Apparatus and Method for Generating an Article

This application is a continuation of U.S. Non-provisional patent application Ser. No. 19/089,264, filed on Mar. 25, 2025, and entitled “APPARATUS AND METHOD FOR GENERATING AN ARTICLE,” which is a continuation-in-part of U.S. Non-provisional patent application Ser. No. 18/368,720, filed on Sep. 15, 2023, now U.S. Pat. No. 12,293,149, and entitled “APPARATUS AND METHOD FOR GENERATING AN ARTICLE,” which is a continuation-in-part of U.S. Non-provisional application Ser. No. 18/127,258, filed on Mar. 28, 2023, now U.S. Pat. No. 11,868,313, issued on Jan. 9, 2024, and entitled “APPARATUS AND METHOD FOR GENERATING AN ARTICLE,” the entirety of each of which is incorporated herein by reference.

The present invention generally relates to the field of literary works. In particular, the present invention is directed to an apparatus and method for generating an activity report.

Articles are time-consuming and sometimes difficult for journalists to write. Current methods of generating reports are insufficient. There is a need for optimized generation of reports using a computing device in a manner that preserves factual accuracy.

In some aspects, the techniques described herein relate to an apparatus for generating a report. The apparatus includes at least a processor, and a memory communicatively connected to the at least a processor, wherein the memory contains instructions configuring the at least a processor to receive a plurality of structured data from a plurality of structured data sources, wherein the plurality of structured data includes event data associated with an activity, determine an activity classification as a function of the plurality of structured data by applying a plurality of activity conditions to the event data, wherein the activity classification includes an activity identifier identifying key facts related to the activity, select an article template including a plurality of spaces for receiving content data as a function of the activity classification, match at least a portion of the content data associated with the event data to a corresponding space of the plurality of spaces of the article template as a function of the activity identifier, and generate a report using the article template populated with the at least a portion of the content data.

In some aspects, the techniques described herein relate to a method of generating a report. The method includes receiving, using at least a processor, a plurality of structured data from a plurality of structured data sources, wherein the plurality of structured data includes event data associated with an activity, determining, using the at least a processor, an activity classification as a function of the plurality of structured data by applying a plurality of activity conditions to the event data, wherein the activity classification includes an activity identifier identifying key facts related to the activity, selecting, using the at least a processor, an article template including a plurality of spaces for receiving content data as a function of the activity classification, matching, using the at least a processor, at least a portion of the content data associated with the event data to a corresponding space of the plurality of spaces of the article template as a function of the activity identifier, and generating, using the at least a processor, a report using the article template populated with the at least a portion of the content data.

These and other aspects and features of non-limiting embodiments of the present invention will become apparent to those skilled in the art upon review of the following description of specific non-limiting embodiments of the invention in conjunction with the accompanying drawings.

The drawings are not necessarily to scale and may be illustrated by phantom lines, diagrammatic representations, and fragmentary views. In certain instances, details that are not necessary for an understanding of the embodiments or that render other details difficult to perceive may have been omitted.

At a high level, aspects of the present disclosure are directed to apparatuses and methods for generating an article. In an embodiment, an article may include a literary work containing different writing styles and formats.

Aspects of the present disclosure can be used to optimize classification of data to generate an article. Aspects of the present disclosure can also be used to augment articles to incorporate a tailored writing style. Aspects of the present disclosure can also be used to aggregate a plurality of articles into a new article.

Exemplary embodiments illustrating aspects of the present disclosure are described below in the context of several specific examples.

1 FIG. 100 100 104 104 108 112 108 112 108 108 112 104 104 104 104 104 104 104 104 104 Referring now to, an exemplary embodiment of apparatusfor system improvement data is illustrated. Apparatusincludes a computing device. Computing deviceincludes a processorand a memorycommunicatively connected to the processor, wherein memorycontains instructions configuring processorto conduct the generating process. Processorand memoryare contained in computing device. Computing devicemay include any computing device as described in this disclosure, including without limitation a microcontroller, microprocessor, digital signal processor (DSP) and/or system on a chip (SoC) as described in this disclosure. Computing device may include, be included in, and/or communicate with a mobile device such as a mobile telephone or smartphone. Computing devicemay include a single computing device operating independently, or may include two or more computing device operating in concert, in parallel, sequentially or the like; two or more computing devices may be included together in a single computing device or in two or more computing devices. Computing devicemay interface or communicate with one or more additional devices as described below in further detail via a network interface device. Network interface device may be utilized for connecting computing deviceto one or more of a variety of networks, and one or more devices. Examples of a network interface device include, but are not limited to, a network interface card (e.g., a mobile network interface card, a LAN card), a modem, and any combination thereof. Examples of a network include, but are not limited to, a wide area network (e.g., the Internet, an enterprise network), a local area network (e.g., a network associated with an office, a building, a campus or other relatively small geographic space), a telephone network, a data network associated with a telephone/voice provider (e.g., a mobile communications provider data and/or voice network), a direct connection between two computing devices, and any combinations thereof. A network may employ a wired and/or a wireless mode of communication. In general, any network topology may be used. Information (e.g., data, software etc.) may be communicated to and/or from a computer and/or a computing device. Computing devicemay include but is not limited to, for example, a computing device or cluster of computing devices in a first location and a second computing device or cluster of computing devices in a second location. Computing devicemay include one or more computing devices dedicated to data storage, security, distribution of traffic for load balancing, and the like. Computing devicemay distribute one or more computing tasks as described below across a plurality of computing devices of computing device, which may operate in parallel, in series, redundantly, or in any other manner used for distribution of tasks or memory between computing devices. Computing devicemay be implemented using a “shared nothing” architecture in which data is cached at the worker, in an embodiment, this may enable scalability of system and/or computing device.

1 FIG. 104 104 104 With continued reference to, computing devicemay be designed and/or configured to perform any method, method step, or sequence of method steps in any embodiment described in this disclosure, in any order and with any degree of repetition. For instance, computing devicemay be configured to perform a single step or sequence repeatedly until a desired or commanded outcome is achieved; repetition of a step or a sequence of steps may be performed iteratively and/or recursively using outputs of previous repetitions as inputs to subsequent repetitions, aggregating inputs and/or outputs of repetitions to produce an aggregate result, reduction or decrement of one or more variables such as global variables, and/or division of a larger processing task into a set of iteratively addressed smaller processing tasks. Computing devicemay perform any step or sequence of steps as described in this disclosure in parallel, such as simultaneously and/or substantially simultaneously performing a step two or more times using two or more parallel threads, processor cores, or the like; division of tasks between parallel threads and/or processes may be performed according to any protocol suitable for division of tasks between iterations. Persons skilled in the art, upon reviewing the entirety of this disclosure, will be aware of various ways in which steps, sequences of steps, processing tasks, and/or data may be subdivided, shared, or otherwise dealt with using iteration, recursion, and/or parallel processing.

1 FIG. 104 116 116 116 116 Still referring to, computing deviceis configured to receive a content category. A “content category,” as used herein, is a type of article. An “article,” as used herein, is literary work. As non-limiting examples, types of articles may include obituaries, weather reports, crime reports, real estate reports, stock reports, and the like. Content categorymay be determined from a machine learning model. The machine learning model may include one or more of the machine learning models as described herein. Additionally and/or alternatively, the content categorymay be determined using a machine-learning algorithm that may rely on rule-based logic, keyword analysis, natural language processing (NLP) techniques, or a combination thereof. Content categorymay be from a user selection. A user selection may be received as a user input. A “user input,” as used herein, is information received from a user. For example, a user input may be the selection or submission of data by a user. A user input may include data logging user interaction with a graphical user interface (GUI). For example, clicking an icon, selecting from a dropdown list, using a touch screen, textual entry, voice recognition, and the like. A “graphical user interface,” as used herein, is a form of user interface that allows users to interact with electronic devices through graphical icons and audio indicator such as primary notation, instead of text-based UIs, typed command labels or text navigation.

1 FIG. 104 120 124 120 120 124 116 116 124 116 124 124 124 120 128 120 124 120 124 124 Still referring to, computing deviceis configured to receive a data filecontaining content data. A “data file,” as used herein, is a data store storing information to be used by a computer. Data filemay include any conventional file for storing data. Data filemay include an Excel file, a .csv file, a .txt file., and the like. “Content data,” as used herein, is contextual information. Content datamay include a plurality of data related to a certain content category. As a non-limiting example, for a content categoryof “obituary,” content datamay include information such as names of people and their date of death. As a non-limiting example, content categoryof “real estate,” content datamay contain information such as addresses of houses, sale dates, and sale prices. In some embodiments, content datamay contain data simultaneously related to a plurality of content categories. For example, content datamay include data that is simultaneously related to an obituary type of article and a real estate type of article. Data filemay contain a plurality of headersdenoting types of data. As non-limiting examples, in the context of real estate, this may include address, sale price, sale date, buyer, seller, property type, and the like. A “header,” used herein, is categorization of data in a data file. This may relate to organizational classification of content datain a file or data structure. For example, in a word document type of data file, there may be a series of columns containing content data, wherein each labeled column is a categorization of a type of data, such as content datarelated to address, contact information, and the like.

1 FIG. 120 132 104 120 132 120 104 100 120 124 128 120 Still referring to, in some embodiments, data filemay be received from a GUI or a user database. A “user database,” as used herein, is a data structure containing data received from user. Databases as described through this disclosure may be implemented, without limitation, as a relational database, a key-value retrieval database such as a NOSQL database, or any other format or structure for use as a database that a person skilled in the art would recognize as suitable upon review of the entirety of this disclosure. Databases may alternatively or additionally be implemented using a distributed data storage protocol and/or data structure, such as a distributed hash table or the like. Databases may include a plurality of data entries and/or records as described above. Data entries in a database may be flagged with or linked to one or more additional elements of information, which may be reflected in data entry cells and/or in linked tables such as tables related by one or more indices in a relational database. Persons skilled in the art, upon reviewing the entirety of this disclosure, will be aware of various ways in which data entries in a database may store, retrieve, organize, and/or reflect data and/or records as used herein, as well as categories and/or populations of data consistently with this disclosure. Computing devicemay be configured to access database and/or retrieve data filewithin user databasethrough one or more database queries. In other embodiments, receiving data filemay include one or more application program interface (API), wherein the application programming interface is a way for two or more devices and or programs to communicate with each other. In a non-limiting example, computing devicewithin apparatusmay be configured to gather data filethrough the application programming interface. “Gather,” as used herein, refers to extracting content dataand headersfrom resources to form a data file.

1 FIG. 104 116 120 132 120 120 120 120 Still referring to, computing devicemay receive content categoryand data filethrough a representational state transfer application programming interface (REST API). An “application programming interface,” as used herein, is a set of rules that define how applications or devices can connect to and communicate with each other. A “representational state transfer application programming interface,” as used herein is an API that conforms to the representational state transfer architectural style. REST APIs as described in this disclosure may communicate via HTTP requests to perform standard database functions like creating, reading, updating, and deleting records within a resource, such as user database. For example, a REST API may use a GET request to retrieve a data file, a POST request to create data file, a PUT request to update data file, and/or a DELETE request to delete data file.

1 FIG. 104 116 120 116 120 Still referring to, computing devicemay receive content categoryand data filethrough RSS (RDF Site Summary or Really Simple Syndication) feeds. “RSS,” as used herein, is a web feed that allows users and applications to access updates to websites in a standardized, computer-readable format. Websites may use RSS feeds to publish frequently updated information, such as blog entries, news headlines, episodes of audio and video series, or for distributing podcasts. An RSS document (called “feed”, “web feed”, or “channel”) may include full or summarized text, and metadata, like publishing date and author's name. RSS document may include content categoryand data file.

1 FIG. 120 104 124 124 128 120 132 104 116 104 124 116 104 104 124 124 Still referring togathering data filemay include using a web crawler. Computing devicemay train and utilize a web crawler to gather content dataand generate a web index of the content data. A “web crawler,” as used herein, is a program that systematically browses the internet for the purpose of web indexing. A “web index,” as used herein is information gathered by a web crawler indexed into a data structure. The web index may be the headersof a data file. The web index may be stored in user database. Computing devicemay generate a query to retrieve data indexed in a data structure as a function of the web crawler as described further below. The web crawler may be seeded with platform URLs, wherein the crawler may then visit the next related URL, retrieve the content, index the content, and/or measures the relevance of the content to the content category. In some embodiments, computing devicemay generate a web crawler to scrape content datafrom a plurality content categoryrelated websites. For example, research websites, social media platforms, content-based forums, and the like. The web crawler may be seeded and/or trained with a website to begin the search. A web crawler may be generated by computing device. In some embodiments, the web crawler may be trained with information received from a user through a graphical user interface. In some embodiments, the web crawler may be configured to generate a web query. A web query may include a search criterion received from a user or generated by computing device. Additionally, the web crawler function may be configured to search for and/or detect one or more data patterns. A “data pattern” as used in this disclosure is any repeating forms of information. A data pattern may include repeating negative or positive reviews by people and the like. In some embodiments, the web crawler may be configured to determine the relevancy of a data pattern. Relevancy may be determined by a relevancy score. A relevancy score may be automatically generated by computing, received from a machine learning model, and/or received from the user. In some embodiments, a relevancy score may include a range of numerical values that may correspond to a relevancy strength of data received from a web crawler function. As a non-limiting example, a web crawler function may search the Internet for content datarelated to current weather trends. The web crawler may return content data, such as, as non-limiting examples, news reports of skyrocketing temperatures, melting ice caps, and the like.

1 FIG. 120 132 Still referring to, in some embodiments, gathering data filemay include processing documents in user databaseusing optical character recognition. Optical character recognition or optical character reader (OCR) includes automatic conversion of images of written (e.g., typed, handwritten or printed text) into machine-encoded text. In some cases, recognition of at least a keyword from an image component may include one or more processes, including without limitation optical character recognition (OCR), optical word recognition, intelligent character recognition, intelligent word recognition, and the like. In some cases, OCR may recognize written text, one glyph or character at a time. In some cases, optical word recognition may recognize written text, one word at a time, for example, for languages that use a space as a word divider. In some cases, intelligent character recognition (ICR) may recognize written text one glyph or character at a time, for instance by employing machine learning processes. In some cases, intelligent word recognition (IWR) may recognize written text, one word at a time, for instance by employing machine learning processes.

1 FIG. Still referring to, in some cases OCR may be an “offline” process, which analyses a static document or image frame. In some cases, handwriting movement analysis can be used as input to handwrite recognition. For example, instead of merely using shapes of glyphs and words, this technique may capture motions, such as the order in which segments are drawn, the direction, and the pattern of putting the pen down and lifting it. This additional information can make handwriting recognition more accurate. In some cases, this technology may be referred to as “online” character recognition, dynamic character recognition, real-time character recognition, and intelligent character recognition.

1 FIG. Still referring to, in some cases, OCR processes may employ pre-processing of image component. Pre-processing process may include without limitation de-skew, de-speckle, binarization, line removal, layout analysis or “zoning,” line and word detection, script recognition, character isolation or “segmentation,” and normalization. In some cases, a de-skew process may include applying a transform (e.g., homography or affine transform) to image component to align text. In some cases, a de-speckle process may include removing positive and negative spots and/or smoothing edges. In some cases, a binarization process may include converting an image from color or greyscale to black-and-white (i.e., a binary image). Binarization may be performed as a simple way of separating text (or any other desired image component) from a background of image component. In some cases, binarization may be required for example if an employed OCR algorithm only works on binary images. In some cases. A line removal process may include removal of non-glyph or non-character imagery (e.g., boxes and lines). In some cases, a layout analysis or “zoning” process may identify columns, paragraphs, captions, and the like as distinct blocks. In some cases, a line and word detection process may establish a baseline for word and character shapes and separate words, if necessary. In some cases, a script recognition process may, for example in multilingual documents, identify script allowing an appropriate OCR algorithm to be selected. In some cases, a character isolation or “segmentation” process may separate signal characters, for example character-based OCR algorithms. In some cases, a normalization process may normalize aspect ratio and/or scale of image component.

1 FIG. Still referring to, in some embodiments an OCR process will include an OCR algorithm. Exemplary OCR algorithms include matrix matching process and/or feature extraction processes. Matrix matching may involve comparing an image to a stored glyph on a pixel-by-pixel basis. In some case, matrix matching may also be known as “pattern matching,” “pattern recognition,” and/or “image correlation.” Matrix matching may rely on an input glyph being correctly isolated from the rest of the image component. Matrix matching may also rely on a stored glyph being in a similar font and at a same scale as input glyph. Matrix matching may work best with typewritten text.

1 FIG. Still referring to, in some embodiments, an OCR process may include a feature extraction process. In some cases, feature extraction may decompose a glyph into features. Exemplary non-limiting features may include corners, edges, lines, closed loops, line direction, line intersections, and the like. In some cases, feature extraction may reduce dimensionality of representation and may make the recognition process computationally more efficient. In some cases, extracted feature can be compared with an abstract vector-like representation of a character, which might reduce to one or more glyph prototypes. General techniques of feature detection in computer vision are applicable to this type of OCR. In some embodiments, machine-learning process like nearest neighbor classifiers (e.g., k-nearest neighbors algorithm) can be used to compare image features with stored glyph features and choose a nearest match. OCR may employ any machine-learning process described in this disclosure. Exemplary non-limiting OCR software includes Cuneiform and Tesseract. Cuneiform is a multi-language, open-source optical character recognition system originally developed by Cognitive Technologies of Moscow, Russia. Tesseract is free OCR software originally developed by Hewlett-Packard of Palo Alto, California, United States.

1 FIG. Still referring to, in some cases, OCR may employ a two-pass approach to character recognition. Second pass may include adaptive recognition and use letter shapes recognized with high confidence on a first pass to recognize better remaining letters on the second pass. In some cases, two-pass approach may be advantageous for unusual fonts or low-quality image components where visual verbal content may be distorted. Another exemplary OCR software tool include OCRopus. OCRopus development is led by German Research Centre for Artificial Intelligence in Kaiserslautern, Germany. In some cases, OCR software may employ neural networks, for example neural networks as taught in this disclosure.

1 FIG. Still referring to, in some cases, OCR may include post-processing. For example, OCR accuracy can be increased, in some cases, if output is constrained by a lexicon. A lexicon may include a list or set of words that are allowed to occur in a document. In some cases, a lexicon may include, for instance, all the words in the English language, or a more technical lexicon for a specific field. In some cases, an output stream may be a plain text stream or file of characters. In some cases, an OCR process may preserve an original layout of visual verbal content. In some cases, near-neighbor analysis can make use of co-occurrence frequencies to correct errors, by noting that certain words are often seen together. For example, “Washington, D.C.” is generally far more common in English than “Washington DOC.” In some cases, an OCR process may make us of a priori knowledge of grammar for a language being recognized. For example, grammar rules may be used to help determine if a word is likely to be a verb or a noun. Distance conceptualization may be employed for recognition and classification. For example, a Levenshtein distance algorithm may be used in OCR post-processing to further optimize results.

1 FIG. 108 With continued reference to, the at least a processormay convert unstructured data into structured data using one or more of OCR process, natural language processing (NLP), and machine learning methods. In an embodiment, OCR process may be utilized to extract text from images, scanned documents, or handwritten content, allowing for the digitization and categorization of textual data. Without limitation the NLP may be applied to analyze, interpret, and structure textual information by identifying key entities, grammatical structures, or semantic relationships within the data. Additionally and/or alternatively, machine learning methods may be implemented to classify, segment, and standardize unstructured data based on learned patterns, contextual features, or predefined rules. This may be done using a language processing model. language processing model may include a natural language process classification model that enumerates and/or derives statistical relationships between input terms and output terms. Algorithm to generate language processing model may include a stochastic gradient descent algorithm, which may include a method that iteratively optimizes an objective function, such as an objective function representing a statistical estimation of relationships between terms, including relationships between input terms and output terms, in the form of a sum of relationships to be estimated. In an alternative or additional approach, sequential tokens may be modeled as chains, serving as the observations in a Hidden Markov Model (HMM). HMMs as used herein are statistical models with inference algorithms that may be applied to the models. In such models, a hidden state to be estimated may include an association between an extracted words, phrases, and/or other semantic units. There may be a finite number of categories to which an extracted word may pertain; an HMM inference algorithm, such as the forward-backward algorithm or the Viterbi algorithm, may be used to estimate the most likely discrete state given a word or sequence of words. Language processing module may combine two or more approaches. For instance, and without limitation, machine-learning program may use a combination of Naive-Bayes (NB), Stochastic Gradient Descent (SGD), and parameter grid-searching classification techniques; the result may include a classification algorithm that returns ranked associations. In some embodiments, creating language processing model may include generating a vector space, which may be a collection of vectors, defined as a set of mathematical objects that can be added together under an operation of addition following properties of associativity, commutativity, existence of an identity element, and existence of an inverse element for each vector, and can be multiplied by scalar values under an operation of scalar multiplication compatible with field multiplication, and that has an identity element is distributive with respect to vector addition, and is distributive with respect to field addition. Each vector in an n-dimensional vector space may be represented by an n-tuple of numerical values. Each unique extracted word and/or language element as described above may be represented by a vector of the vector space. In an embodiment, each unique extracted and/or other language element may be represented by a dimension of vector space; as a non-limiting example, each element of a vector may include a number representing an enumeration of co-occurrences of the word and/or language element represented by the vector with another word and/or language element. Vectors may be normalized, scaled according to relative frequencies of appearance and/or file sizes. In an embodiment associating language elements to one another as described above may include computing a degree of vector similarity between a vector representing each language element and a vector representing another language element; vector similarity may be measured according to any norm for proximity and/or similarity of two vectors, including without limitation cosine similarity, which measures the similarity of two vectors by evaluating the cosine of the angle between the vectors, which can be computed using a dot product of the two vectors divided by the lengths of the two vectors. Degree of similarity may include any other geometric measure of distance between vectors.

1 FIG. 104 124 120 124 124 104 128 120 116 104 120 124 116 104 116 104 124 Still referring to, computing deviceis configured to import content datafrom data file. Importing content datamay include importing data to be displayed through a GUI. Importing content datamay include assessing, by the computing device, headersof the data fileassociated with content category. In this case, computing devicemay receive a data filewherein the headers and content dataare already associated with a content category. For example, computing devicemay receive a word file related to a news alert content categorycontaining associated headers such as times, location, death, source, and the like. Computing devicedevice may import content datacategorized under each header for use in processing methods as described further below to generate article.

1 FIG. 124 120 128 136 124 136 116 124 116 128 140 116 140 104 104 116 124 104 124 136 104 140 116 116 140 116 104 140 104 120 140 140 140 140 104 Still referring to, in some embodiments, importing content datafrom data filemay include classifying a plurality of headersto desired dataof the content data, wherein desired datais related to the content category. “Desired data,” as used herein, is content datarelevant to a content category. Classifying the plurality of headersmay include determining a plurality of desired data headers. A “desired data header,” as a used herein, is a header relevant to a content category. Desired data headersmay be determined by computing deviceusing machine-learning methods and language processing methods as described throughout this disclosure. For example, computing devicemay receive a content categoryof obituary and determine relevant content datathat may be used in generation of the obituary article. Computing devicemay also determine relevant headers, as in categories of content data, required for the generation of the article. For example, headers related to desired datafor an obituary may include, “name,” “date of death,” “cause,” and the like. In some embodiments, computing devicemay receive desired data headersassociated with a content categoryfrom an article database. An “article database,” as used herein, is a data structure containing data used in the generation of an article. For example, the article database may include a content categoryindex containing desired data headersassociated with each content category. In some embodiments, computing devicemay receive the desired data to classify to a desired data headeras a user input received through a GUI. For example, computing devicemay receive data file, extract the desired data headerscontained within, and present the plurality of desired data headersextracted to a user through a GUI. A user may then manually match desired data to the corresponding desired data headerby user input. For example, a user may enter through textual submission that the desired data corresponding to a “cause” desired data headerin an obituary as “stupidity”. In some embodiments, computing devicemay match desired data to the corresponding desired header using a machine-learning model as described further below.

1 FIG. 104 104 Still referring to, in some embodiments, classifying the headers to the desired data may include using a matching machine-learning model, also referred to as s matching classifier. Matching machine learning model may include a classifier. A “classifier,” as used in this disclosure is a machine-learning model, such as a mathematical model, neural net, or program generated by a machine learning algorithm known as a “classification algorithm,” as described in further detail below, that sorts inputs into categories or bins of data, outputting the categories or bins of data and/or labels associated therewith. A classifier may be configured to output at least a datum that labels or otherwise identifies a set of data that are clustered together, found to be close under a distance metric as described below, or the like. Computing deviceand/or another device may generate a classifier using a classification algorithm, defined as a processes whereby a computing devicederives a classifier from training data. Classification may be performed using, without limitation, linear classifiers such as without limitation logistic regression and/or naive Bayes classifiers, nearest neighbor classifiers such as k-nearest neighbors classifiers, support vector machines, least squares support vector machines, fisher's linear discriminant, quadratic classifiers, decision trees, boosted trees, random forest classifiers, learning vector quantization, and/or neural network-based classifiers.

1 FIG. 104 104 104 Still referring to, computing devicemay be configured to generate classifiers as used in this disclosure using a Naïve Bayes classification algorithm. Naïve Bayes classification algorithm generates classifiers by assigning class labels to problem instances, represented as vectors of element values. Class labels are drawn from a finite set. Naïve Bayes classification algorithm may include generating a family of algorithms that assume that the value of a particular element is independent of the value of any other element, given a class variable. Naïve Bayes classification algorithm may be based on Bayes Theorem expressed as P(A/B)=P(B/A) P(A)÷P(B), where P(A/B) is the probability of hypothesis A given data B also known as posterior probability; P(B/A) is the probability of data B given that the hypothesis A was true; P(A) is the probability of hypothesis A being true regardless of data also known as prior probability of A; and P(B) is the probability of the data regardless of the hypothesis. A naïve Bayes algorithm may be generated by first transforming training data into a frequency table. Computing devicemay then calculate a likelihood table by calculating probabilities of different data entries and classification labels. Computing devicemay utilize a naïve Bayes equation to calculate a posterior probability for each class. A class containing the highest posterior probability is the outcome of prediction. Naïve Bayes classification algorithm may include a gaussian model that follows a normal distribution. Naïve Bayes classification algorithm may include a multinomial model that is used for discrete counts. Naïve Bayes classification algorithm may include a Bernoulli model that may be utilized when vectors are binary.

1 FIG. 104 With continued reference to, computing devicemay be configured to generate classifiers as used in this disclosure using a K-nearest neighbors (KNN) algorithm. A “K-nearest neighbors algorithm” as used in this disclosure, includes a classification method that utilizes feature similarity to analyze how closely out-of-sample-features resemble training data to classify input data to one or more clusters and/or categories of features as represented in training data; this may be performed by representing both training data and input data in vector forms, and using one or more measures of vector similarity to identify classifications within training data, and to determine a classification of input data. K-nearest neighbors algorithm may include specifying a K-value, or a number directing the classifier to select the k most similar entries training data to a given sample, determining the most common classifier of the entries in the database, and classifying the known sample; this may be performed recursively and/or iteratively to generate a classifier that may be used to classify input data as further samples. For instance, an initial set of samples may be performed to cover an initial heuristic and/or “first guess” at an output and/or relationship, which may be seeded, without limitation, using expert input received according to any process as described herein. As a non-limiting example, an initial heuristic may include a ranking of associations between inputs and elements of training data. Heuristic may include selecting some number of highest-ranking associations and/or training data elements.

1 FIG. With continued reference to, generating k-nearest neighbors algorithm may generate a first vector output containing a data entry cluster, generating a second vector output containing an input data, and calculate the distance between the first vector output and the second vector output using any suitable norm such as cosine similarity, Euclidean distance measurement, or the like. Each vector output may be represented, without limitation, as an n-tuple of values, where n is at least two values. Each value of n-tuple of values may represent a measurement or other quantitative value associated with a given category of data, or attribute, examples of which are provided in further detail below; a vector may be represented, without limitation, in n-dimensional space using an axis per category of value represented in n-tuple of values, such that a vector has a geometric direction characterizing the relative quantities of attributes in the n-tuple as compared to each other. Two vectors may be considered equivalent where their directions, and/or the relative quantities of values within each vector as compared to each other, are the same; thus, as a non-limiting example, a vector represented as [5, 10, 15] may be treated as equivalent, for purposes of this disclosure, as a vector represented as [1, 2, 3]. Vectors may be more similar where their directions are more similar, and more different where their directions are more divergent; however, vector similarity may alternatively or additionally be determined using averages of similarities between like attributes, or any other measure of similarity suitable for any n-tuple of values, or aggregation of numerical similarity measures for the purposes of loss functions as described in further detail below. Any vectors as described herein may be scaled, such that each vector represents each attribute along an equivalent scale of values. Each vector may be “normalized,” or divided by a “length” attribute, such as a length attribute l as derived using a Pythagorean norm:

i where ais attribute number i of the vector. Scaling and/or normalization may function to make vector comparison independent of absolute quantities of attributes, while preserving any dependency on similarity of attributes; this may, for instance, be advantageous where cases represented in training data are represented by different quantities of samples, which may result in proportionally equivalent vectors with divergent values.

1 FIG. 144 124 140 124 140 144 120 136 140 116 144 144 140 Still referring to, matching classifiermay be configured to classify desired data of content datato the corresponding desired data header. For example, content datasuch as “light rain” and “high wind” may be classified to a desired data headerof “type of weather.” Matching classifiermay be trained using desired content training data correlating data fileto data files with headers matched to desired data, desired data headersto content categories, and the like. In some embodiments, matching classifiermay be trained using data collected by the manual matching of the headers to the desired data as a function of a user input as discussed above. Matching classifier, as a function of the desired content training data, may output each desired data headermatch to the corresponding desired data.

1 FIG. 104 148 124 116 104 148 152 Still referring to, computing deviceis configured to generate an articleas a function of the imported content dataand content category. Computing devicemay generate articleutilizing an article module. An “article module,” as used herein is a set of processing models working in tandem to generate an article. Article module may include a plurality of classifiers and machine-learning models or processes to create an article temples, classify data to the template, and optimize the linguistics of the article. In some embodiments, article module may include a template classifier, article classifier, language processing model, and/or a smoothing language filter as described further below.

104 116 116 120 116 120 120 124 128 124 116 116 116 Computing devicemay use a template classifier to match content categoryand/or contents of data file to a corresponding article template. An “article template,” as used herein, is a data structure outlining data to be populated to create an article. For example, an article template for an obituary may include an intro (e.g., name of deceased, names of family members), discussion (e.g., cause of death, life biography), and a conclusion (e.g., name of cemetery, date of funeral) space. For example, template classifier may be trained by training data correlating a plurality of content category and data file types to corresponding article templates. Template classifier may receive content categoryand data fileand output a corresponding article template. In some embodiments each content categorymay have an article template stored in article database. In some embodiments, the article template may be repeated for every set of headers, desired, data, and the like the imported from data file. In some embodiments, computing device may additionally or alternatively use a language process model to classify contents of data fileto an appropriate article template. The article template output by the template classifier may then be used as input in an article classifier configured to match the contents of data to the corresponding spaces of the article temple. This may include designating the arrangement of content dataand headers. For example, the intro section of an obituary article template may prompt for the deceased name and name of family members. Article classifier may match corresponding content data by identifying words and phrases that match the prompt. In other words, article classifier may be a classifier configured to receive imported content data, such as the desired headers and corresponding desired data, and content categoryas an input and output article. Article classifier may be trained by training data received from article database. Article training data may include data correlating imported content categoryto an article template. Article training data may include a dictionary. A “dictionary,” as used herein, is a data structure containing information related to linguistics. “Linguistics,” as used herein, is the scientific study of human language. The dictionary may include rules and examples regarding syntax (rules governing the structure of sentences); semantics (meaning); morphology (structure of words); phonetics (speech sounds and equivalent gestures in sign languages); phonology (the abstract sound system of a particular language); pragmatics (how social context contributes to meaning), and the like. Article training data may also include boilerplate data. “Boilerplate data,” as used herein, is data regarding to standardized text of an article that can be used repeatedly without making major changes. In some cases, boilerplate data may be selected by the user. In a non-limiting example, boilerplate data may be received from a user. In a non-limiting example, user may be able to customize boilerplate data by editing text within boilerplate data. In some embodiments, boilerplate data may include, without limitation, an AI disclaimer, links to a membership service, links to a homepage, and the like thereof. In some cases, boilerplate data may be placed at the end of article. In a non-limiting example, generating article may include inserting boilerplate correlated to a content category. In some embodiments, boilerplate data may include a signature of the user (i.e., author or individual who generates article) and/or a copyright notice or other legal notice.

1 FIG. 148 148 124 148 148 Still referring to, articlemay then go through a smoothing language filter. A “smoothing language filter,” as used herein, is a machine-learning model configured to identify a degree of change between language elements of an article. For example, smoothing language filter may access how “jarring,” or “sharp,” the transition is from one word to the next word or a phrase to the next phrase. Smoothing language filter may be used to assess the linguistic flow of articleusing a scoring algorithm based on the degree of change. For example, the scoring algorithm may rate the linguistic flow of content datain each section or header of articleon a scale of 1-10, a percentage, linguistic metric and the like. The replacement, or rearrangement of words and phrases may be modified based on the score. For example if a discussion section of articlescores lower than a predetermined threshold set by the computer or a user input, computing device may reiteratively generate the section of the article using methods as described above until the score is acceptable. For example, article classifier may receive the low ranked section as an input or as training data as an example regarding an arrangement of words or phrases to avoid. Smoothing language filter may be trained by training data correlating scores of the scoring algorithm to a plurality of articles the article database. In some embodiments, scoring the linguistic flow may use a neural network or deep learning techniques as described further below.

1 FIG. 124 148 104 148 148 124 Still referring to, in some embodiments, the degree of change may be assessed using fuzzy logic. In fuzzy logic, values of system variables may be expressed in linguistic terms such as “jarring,” “sharp” and “enticing,” which designate regions of interest in a data set. These linguistic expressions are referred to as fuzzy sets in this application. A fuzzy set may also be used to show degree of match between fuzzy sets and may be used to rank one language element over another. Each metric of a linguistic scoring algorithm may be represented as a fuzzy set. For example, a phonetics fuzzy set, syntax fuzzy, semantics fuzzy set, and the like. These plurality of fuzzy sets may be used to assess each section of content datain article. For example, the intro section may be presented as phonetics, syntax, and semantics fuzzy sets. Each linguistic metric to be compared to ideal linguistic metrics may be represented using a linguistic variable on a range of potential numerical values, where values for the linguistic variable may be represented as fuzzy sets on that range; where values for the linguistic variable may be represented as fuzzy sets on that range; a “natural” or “good” fuzzy set may correspond to a range of values that can be characterized as ideal, while other fuzzy sets may correspond to ranges that can be characterized as mediocre, bad, or other less-than-ideal ranges and/or values. Fuzzy logic may combine such linguistic variable values according to one or more fuzzy logic rules, including training data as disclosed herein (i.e., dictionary), any type of fuzzy logic and/or rules as described in this disclosure, to determine a degree of membership in one or more output linguistic variables having values representing ideal linguistic flow, mediocre or middling linguistic flow, and/or low or poor linguistic flow. Computing devicemay modify sections of articlebased on the plurality of linguistic variable metrics. For example if the syntax fuzzy set of the conclusion section of articlescored “poor”, below a predetermined threshold, then content dataof that section may be regenerated using the article classifier as described above. In some embodiments, linguistics scores of the fuzzy sets may be added as training data of the article classifier as examples of arrangement of words or phrases to avoid or model.

1 FIG. 148 With continued reference to, in some embodiments, generating articlemay include using a language processing module. Language processing module may include any hardware and/or software module. Language processing module may be configured to extract, from the one or more documents, one or more words. One or more words may include, without limitation, strings of one or more characters, including without limitation any sequence or sequences of letters, numbers, punctuation, diacritic marks, engineering symbols, geometric dimensioning and tolerancing (GD&T) symbols, chemical symbols and formulas, spaces, whitespace, and other symbols, including any symbols usable as textual data as described above. Textual data may be parsed into tokens, which may include a simple word (sequence of letters separated by whitespace) or more generally a sequence of characters as described previously. Tokens may be broken up by word, pair of words, sentence, or other delimitation. These tokens may in turn be parsed in various ways. Textual data may be parsed into words or sequences of words, which may be considered words as well. Textual data may be parsed into “n-grams”, where all sequences of n consecutive characters are considered. Any or all possible sequences of tokens or words may be stored as “chains”, for example for use as a Markov chain or Hidden Markov Model.

1 FIG. 104 104 With continued reference to, language processing module may operate to produce a language processing model. Language processing model may include a program automatically generated by computing deviceand/or language processing module to produce associations between one or more words extracted from at least a document and detect associations, including, without limitation, mathematical associations, between such words. Associations between language elements, where language elements include for purposes herein extracted words, relationships of such categories to other such term may include, without limitation, mathematical associations, including without limitation statistical correlations between any language element and any other language element and/or language elements. Statistical correlations and/or mathematical associations may include probabilistic formulas or relationships indicating, for instance, a likelihood that a given extracted word indicates a given category of semantic meaning. As a further example, statistical correlations and/or mathematical associations may include probabilistic formulas or relationships indicating a positive and/or negative association between at least an extracted word and/or a given semantic meaning; positive or negative indication may include an indication that a given document is or is not indicating a category semantic meaning. Whether a phrase, sentence, word, or other textual element in a document or corpus of documents constitutes a positive or negative indicator may be determined, in an embodiment, by mathematical associations between detected words, comparisons to phrases and/or words indicating positive and/or negative indicators that are stored in memory at computing device, or the like.

1 FIG. With continued reference to, language processing module and/or diagnostic engine may generate the language processing model by any suitable method, including without limitation a natural language processing classification algorithm; language processing model may include a natural language process classification model that enumerates and/or derives statistical relationships between input terms and output terms. Algorithm to generate language processing model may include a stochastic gradient descent algorithm, which may include a method that iteratively optimizes an objective function, such as an objective function representing a statistical estimation of relationships between terms, including relationships between input terms and output terms, in the form of a sum of relationships to be estimated. In an alternative or additional approach, sequential tokens may be modeled as chains, serving as the observations in a Hidden Markov Model (HMM). HMMs has used herein are statistical models with inference algorithms that may be applied to the models. In such models, a hidden state to be estimated may include an association between an extracted word, phrases, and/or other semantic units. There may be a finite number of categories to which an extracted word may pertain; an HMM inference algorithm, such as the forward-backward algorithm or the Viterbi algorithm, may be used to estimate the most likely discrete state given a word or sequence of words. Language processing module may combine two or more approaches. For instance, and without limitation, machine-learning program may use a combination of Naive-Bayes (NB), Stochastic Gradient Descent (SGD), and parameter grid-searching classification techniques; the result may include a classification algorithm that returns ranked associations.

1 FIG. With continued reference to, generating language processing model may include generating a vector space, which may be a collection of vectors, defined as a set of mathematical objects that can be added together under an operation of addition following properties of associativity, commutativity, existence of an identity element, and existence of an inverse element for each vector, and can be multiplied by scalar values under an operation of scalar multiplication compatible with field multiplication, and that has an identity element is distributive with respect to vector addition, and is distributive with respect to field addition. Each vector in an n-dimensional vector space may be represented by an n-tuple of numerical values. Each unique extracted word and/or language element as described above may be represented by a vector of the vector space. In an embodiment, each unique extracted and/or other language element may be represented by a dimension of vector space; as a non-limiting example, each element of a vector may include a number representing an enumeration of co-occurrences of the word and/or language element represented by the vector with another word and/or language element. Vectors may be normalized, scaled according to relative frequencies of appearance and/or file sizes. In an embodiment associating language elements to one another as described above may include computing a degree of vector similarity between a vector representing each language element and a vector representing another language element; vector similarity may be measured according to any norm for proximity and/or similarity of two vectors, including without limitation cosine similarity, which measures the similarity of two vectors by evaluating the cosine of the angle between the vectors, which can be computed using a dot product of the two vectors divided by the lengths of the two vectors. Degree of similarity may include any other geometric measure of distance between vectors.

1 FIG. 104 104 104 With continued reference to, language processing module may use a corpus of documents to generate associations between language elements in a language processing module, and diagnostic engine may then use such associations to analyze words extracted from one or more documents and determine that the one or more documents indicate significance of a category. In an embodiment, language processing module and/or computing devicemay perform this analysis using a selected set of significant documents, such as documents identified by one or more experts as representing good information; experts may identify or enter such documents via graphical user interface, or may communicate identities of significant documents according to any other suitable method of electronic communication, or by providing such identity to other persons who may enter such identifications into computing device. Documents may be entered into a computing deviceby being uploaded by an expert or other persons using, without limitation, file transfer protocol (FTP) or other suitable methods for transmission and/or upload of documents; alternatively or additionally, where a document is identified by a citation, a uniform resource identifier (URI), uniform resource locator (URL) or other datum permitting unambiguous identification of the document, diagnostic engine May automatically obtain the document using such an identifier, for instance by submitting a request to a database or compendium of documents such as JSTOR as provided by Ithaka Harbors, Inc. of New York.

1 FIG. 124 With continued reference to, in some embodiments, language processing module may include a grammatical checker. As used in this disclosure, a “grammatical checker” is a component of language processing module that attempts to verify text (i.e., content data) for grammatical correctness. In a non-limiting example, grammatical checker may include a program that runs simultaneously in the background of the runtime environment of language processing module while generating article. Grammatical checker may automatically correct article during, or after article generation. Correcting article may include, without limitation, grammar, spelling, tense, word choice, and the like thereof.

1 FIG. With continued reference to, in some embodiments, generating the article may be consistent with aspects of generating an activity article as disclosed in U.S. Nonprovisional application Ser. No. 17/993,108, filed on Nov. 23, 2022, and entitled, APPARATUS AND METHOD FOR GENERATING AN ACTIVITY ARTICLE,” the entirety of which is incorporated by reference herein.

1 FIG. Still referring to, generating the article may include editing the article as a function of user input. For example, the user may be able to edit the generated article through a GUI. In some embodiments, the user may be able to edit the generated article using a n online rich text editor. An “online rich-text editor,” is an interface for editing rich text within web browsers, which presents the user with a “what-you-see-is-what-you-get” (WYSIWYG) editing area. The aim is to reduce the effort for users trying to express their formatting directly as valid HTML markup.

1 FIG. 148 148 Still referring to, in some embodiments, generating articlemay further include generating an augmented article. “Augmented,” as used herein, refers to the increase of quality of an article. For example, the augmented article may be a finely-tuned version of articlebased on a trait such as syntax, writing, style impact, and the like. Generating an augmented article may include inputting article generated by article classifier and/or the language processing model into an artificial neural network, wherein the neural network outputs the augmented article. A “neural network,” also known as an artificial neural network, is a network of “nodes,” or data structures having one or more inputs, one or more outputs, and a function determining outputs based on inputs, as described further below. In some embodiments, input to the neural network may additionally include a prompt. A “prompt,” as used herein, is a topic of focus in augmenting an article. The prompt may be any instruction to the neural network relating to the desired content or format of the augmented article. For example, prompt may indicate a desired reading level, a targeted locality, a level of humor, a length, a style of writing, and the like. In some embodiments, the neural network may include a Generative Pre-trained Transformer 3 (GPT-3). A “GPT-3,” as used herein, is an autoregressive language model that uses deep learning to produce human-like text. Given an initial text as prompt, it may produce text that continues the prompt.

1 FIG. Still referring to, generating an augmented article may include training and/or utilizing a large language model (LLM). A “large language model,” as used herein, is a deep learning algorithm that can recognize, summarize, translate, predict and/or generate text and other content based on knowledge gained from massive datasets. LLMs may be trained on large sets of data; for example, training sets may include greater than 1 million words. Training sets may be drawn from diverse sets of data such as, as non-limiting examples, novels, blog posts, articles, emails, and the like. Training sets may include a variety of subject matters, such as, as nonlimiting examples, medical tests, romantic ballads, beat poetry, emails, advertising documents, newspaper articles, and the like. LLMs, in some embodiments, may include GPT, GPT-2, GPT-3, and other language processing models. LLM may be used to augment the text in an article based on a prompt. Training data may correlate content data to plurality of prompts. Training data may correlate elements of a dictionary related to linguistics, as described above, to a prompt. LLM may include a text prediction based algorithm configured to receive an article and apply a probability distribution to the words already typed in a sentence to work out the most likely word to come next in augmented articles. For example, if the words already typed are “Nice to meet,” then it is highly likely that the word “you” will come next. LLM may output such predictions by ranking words by likelihood or a prompt parameter. For the example given above, the LLM may score “you” as the most likely, “your” as the next most likely, “his” or “her” next, and the like.

1 FIG. Still referring to, LLM may include an attention mechanism, utilizing a transformer as described further below. An “attention mechanism,” as used herein, is a part of a neural architecture that enables a system to dynamically highlight relevant features of the input data. In natural language processing this may be a sequence of textual elements. It may be applied directly to the raw input or to its higher-level representation. An attention mechanism may be an improvement to the limitation of the Encoder-Decoder model which encodes the input sequence to one fixed length vector from which to decode the output at each time step. This issue may be seen as a problem when decoding long sequences because it may make it difficult for the neural network to cope with long sentences, such as those that are longer than the sentences in the training corpus. Applying a attention mechanism, LLM may predict the next word by searching for a set of position in a source sentence where the most relevant information is concentrated. LLM may then predict the next word based on context vectors associated with these source positions and all the previous generated target words, such as textual data of a dictionary correlated to a prompt in a training data set. A “context vector,” as used herein, are fixed-length vector representations useful for document retrieval and word sense disambiguation. In some embodiments, LLM may include encoder-decoder model incorporating an attention mechanism.

1 FIG. Still referring to, LLM may include a transformer architecture. In some embodiments, encoder component of LLM may include transformer architecture. A “transformer architecture,” for the purposes of this disclosure is a neural network architecture that uses self-attention and positional encoding. Transformer architecture may be designed to process sequential input data, such as natural language, with applications towards tasks such as translation and text summarization. Transformer architecture may process the entire input all at once. “Positional encoding,” for the purposes of this disclosure, refers to a data processing technique that encodes the location or position of an entity in a sequence. In some embodiments, each position in the sequence may be assigned a unique representation. In some embodiments, positional encoding may include mapping each position in the sequence to a position vector. In some embodiments, trigonometric functions, such as sine and cosine, may be used to determine the values in the position vector. In some embodiments, position vectors for a plurality of positions in a sequence may be assembled into a position matrix, wherein each row of position matrix may represent a position in the sequence.

1 FIG. With continued reference to, LLM and/or transformer architecture may include an attention mechanism. An “attention mechanism,” as used herein, is a part of a neural architecture that enables a system to dynamically quantify the relevant features of the input data. In the case of natural language processing, input data may be a sequence of textual elements. It may be applied directly to the raw input or to its higher-level representation.

1 FIG. With continued reference to, an attention mechanism may represent an improvement over a limitation of the Encoder-Decoder model. The encoder-decider model encodes the input sequence to one fixed length vector from which the output is decoded at each time step. This issue may be seen as a problem when decoding long sequences because it may make it difficult for the neural network to cope with long sentences, such as those that are longer than the sentences in the training corpus. Applying an attention mechanism, LLM may predict the next word by searching for a set of position in a source sentence where the most relevant information is concentrated. LLM may then predict the next word based on context vectors associated with these source positions and all the previous generated target words, such as textual data of a dictionary correlated to a prompt in a training data set. A “context vector,” as used herein, are fixed-length vector representations useful for document retrieval and word sense disambiguation.

1 FIG. Still referring to, an attention mechanism may include generalized attention self-attention, multi-head attention, additive attention, global attention, and the like. In generalized attention, when a sequence of words or an image is fed to LLM, it may verify each element of the input sequence and compare it against the output sequence. Each iteration may involve the mechanism's encoder capturing the input sequence and comparing it with each element of the decoder's sequence. From the comparison scores, the mechanism may then select the words or parts of the image that it needs to pay attention to. In self-attention, LLM may pick up particular parts at different positions in the input sequence and over time compute an initial composition of the output sequence. In multi-head attention, LLM may include a transformer model of an attention mechanism. Attention mechanisms, as described above, may provide context for any position in the input sequence. For example, if the input data is a natural language sentence, the transformer does not have to process one word at a time. In multi-head attention, computations by LLM may be repeated over several iterations, each computation may form parallel layers known as attention heads. Each separate head may independently pass the input sequence and corresponding output sequence element through a separate head. A final attention score may be produced by combining attention scores at each head so that every nuance of the input sequence is taken into consideration. In additive attention (Bahdanau attention mechanism), LLM may make use of attention alignment scores based on a number of factors. These alignment scores may be calculated at different points in a neural network. Source or input sequence words are correlated with target or output sequence words but not to an exact degree. This correlation may take into account all hidden states and the final alignment score is the summation of the matrix of alignment scores. In global attention (Luong mechanism), in situations where neural machine translations are required, LLM may either attend to all source words or predict the target sentence, thereby attending to a smaller subset of words.

1 FIG. With continued reference to, multi-headed attention in encoder may apply a specific attention mechanism called self-attention. Self-attention allows the models to associate each word in the input, to other words. So, as a non-limiting example, the LLM may learn to associate the word “you,” with “how” and “are.” It is also possible that LLM learns that words structured in this pattern are typically a question and to respond appropriately. In some embodiments, to achieve self-attention, input may be fed into three distinct fully connected layers to create query, key, and value vectors. The query, key, and value vectors maybe fed through a linear layer; then, the query and key vectors may be multiplies using dot product matrix multiplication in order to produce a score matrix. The score matrix may determine the amount of focus for a word should be put on other words (thus, each word may be a score that corresponds to other words in the time-step). The values in score matrix may be scaled down. As a non-limiting example, score matrix may be divided by the square root of the dimension of the query and key vectors. In some embodiments, the softmax of the scaled scores in score matrix may be taken. The output of this softmax function may be called the attention weights. Attention weights may be multiplied by your value vector to obtain an output vector. The output vector may then be fed through a final linear layer.

1 FIG. With continued reference to, in order to use self-attention in a multi-headed attention computation, query, key, and value may be split into N vectors before applying self-attention. Each self-attention process may be called a “head.” Each head may produce an output vector and each output vector from each head may be concatenated into a single vector. This single vector may then be fed through the final linear layer discussed above. In theory, each head can learn something different from the input, therefore giving the encoder model more representation power.

1 FIG. With continued reference to, encoder of transformer may include a residual connection. Residual connection may include adding the output from multi-headed attention to the positional input embedding. In some embodiments, the output from residual connection may go through a layer normalization. In some embodiments, the normalized residual output may be projected through a pointwise feed-forward network for further processing. The pointwise feed-forward network may include a couple of linear layers with a ReLU activation in between. The output may then be added to the input of the pointwise feed-forward network and further normalized.

1 FIG. With continued reference to, transformer architecture may include a decoder. Decoder may be a multi-headed attention layer, a pointwise feed-forward layer, one or more residual connections, and layer normalization (particularly after each sub-layer), as discussed in more detail above. In some embodiments, decoder may include two multi-headed attention layers. In some embodiments, decoder may be autoregressive. For the purposes of this disclosure, “autoregressive” means that the decoder takes in a list of previous outputs as inputs along with encoder outputs containing attention information from the input.

1 FIG. With continued reference to, in some embodiments, input to decoder may go through an embedding layer and positional encoding layer in order to obtain positional embeddings. Decoder may include a first multi-headed attention layer, wherein the first multi-headed attention layer may receive positional embeddings.

1 FIG. With continued reference to, first multi-headed attention layer may be configured to not condition to future tokens. As a non-limiting example, when computing attention scores on the word “am,” decoder should not have access to the word “fine” in “I am fine,” because that word is a future word that was generated after. The word “am” should only have access to itself and the words before it. In some embodiments, this may be accomplished by implementing a look-ahead mask. Look ahead mask is a matrix of the same dimensions as the scaled attention score matrix that is filled with “0s” and negative infinities. For example, the top right triangle portion of look-ahead mask may be filed with negative infinities. Look-ahead mask may be added to scaled attention score matrix to obtain a masked score matrix. Masked score matrix may include scaled attention scores in the lower-left triangle of the matrix and negative infinities in the upper-right triangle of the matrix. Then, when the softmax of this matrix is taken, the negative infinities will be zeroed out; this leaves “zero” attention scores for “future tokens.”

1 FIG. With continued reference to, second multi-headed attention layer may use encoder outputs as queries and keys and the outputs from the first multi-headed attention layer as values. This process matches the encoder's input to the decoder's input, allowing the decoder to decide which encoder input is relevant to put a focus on. The output from second multi-headed attention layer may be fed through a pointwise feedforward layer for further processing.

1 FIG. With continued reference to, the output of the pointwise feedforward layer may be fed through a final linear layer. This final linear layer may act as a classifier. This classifier may be as big as the number of classes that you have. For example, if you have 10,000 classes for 10,000 words, the output of that classier will be of size 10,000. The output of this classifier may be fed into a softmax layer which may serve to produce probability scores between zero and one. The index may be taken of the highest probability score in order to determine a predicted word.

1 FIG. With continued reference to, decoder may take this output and add it to the decoder inputs. Decoder may continue decoding until a token is predicted. Decoder may stop decoding once it predicts an end token.

1 FIG. With continued reference to, in some embodiment, decoder may be stacked N layers high, with each layer taking in inputs from the encoder and layers before it. Stacking layers may allow LLM to learn to extract and focus on different combinations of attention from its attention heads.

1 FIG. 148 104 104 116 104 Still referring to, in some embodiments, generating articlemay further include generating an aggregate article. An “aggregate article,” is an article produced by the aggregation of a plurality of articles. Computing devicemay be configured to generate an aggregate article from a plurality of related articles generated or received by computing device. In some embodiments, this may be done periodically—i.e., monthly, weekly, yearly, and the like an update to the original article or as a newly generated article. As a non-limiting example, a content categoryof “real estate,” the augmented article may address trends in real estate (like sale prices) during the period. Computing devicemay generate the aggregated article using article classifier, language processing model, and the neural network as described above. For example, a plurality of related articles may be inputted into article classifier, wherein trends identified using a language processing model is part of the article training data, and article classifier is configured to output the aggregated article. The aggregated article may then be augmented using a neural network as described above.

1 FIG. 104 104 104 104 With continued reference to, computing deviceis configured to export article. As used in this disclosure, “exporting” is converting, outputting, or otherwise exporting article using computing device. In some embodiments, exporting article may include converting article into any data structure described in this disclosure. In some embodiments, article may be exported through RSS feeds to a website as described above. As a nonlimiting example, articles may be added to an RSS feed. In some embodiments, exporting article may include outputting article in a format such as, without limitation, an HTML file, pdf file, text document, word document, and the like thereof. In a non-limiting example, computing devicemay convert text within article into one or more HTML tags using a representational state transfer (REST) API, wherein the REST API is an API that conforms to constraints of REST architectural style (i.e., client-server architecture). User (i.e., client) may initiate conversion of article by requesting server through REST API. Requesting server may include client sending a request such as, without limitation, a POST request and the like. Server may post converted one or more HTML tags to a customer relationship management (CRM) platform, wherein the CRM platform is a system that administer a business or other organization interactions with users through data analysis. CRM platform may include a back-office system containing a plurality of automated processes that is executable by computing device. CRM platform may send a unique identifier of exported article, a HTML file containing one or more converted HTML tags, and a URL to exported article through an email.

2 FIG. 200 Referring now to, an exemplary embodiment of a machine-learning modulethat may perform one or more machine-learning processes as described in this disclosure is illustrated. Machine-learning module may perform determinations, classification, and/or analysis steps, methods, processes, or the like as described in this disclosure using machine learning processes.

2 FIG. 204 204 204 204 204 204 204 Still referring to, “training data,” as used herein, is data containing correlations that a machine-learning process may use to model relationships between two or more categories of data elements. For instance, and without limitation, training datamay include a plurality of data entries, each entry representing a set of data elements that were recorded, received, and/or generated together; data elements may be correlated by shared existence in a given data entry, by proximity in a given data entry, or the like. Multiple data entries in training datamay evince one or more trends in correlations between categories of data elements; for instance, and without limitation, a higher value of a first data element belonging to a first category of data element may tend to correlate to a higher value of a second data element belonging to a second category of data element, indicating a possible proportional or other mathematical relationship linking values belonging to the two categories. Multiple categories of data elements may be related in training dataaccording to various correlations; correlations may indicate causative and/or predictive links between categories of data elements, which may be modeled as relationships such as mathematical relationships by machine-learning processes as described in further detail below. Training datamay be formatted and/or organized by categories of data elements, for instance by associating data elements with one or more descriptors corresponding to categories of data elements. As a non-limiting example, training datamay include data entered in standardized forms by persons or processes, such that entry of a given data element in a given field in a form may be mapped to one or more descriptors of categories. Elements in training datamay be linked to descriptors of categories by tags, tokens, or other data elements; for instance, and without limitation, training datamay be provided in fixed-length formats, formats linking positions of data to categories such as comma-separated value (CSV) formats and/or self-describing formats such as extensible markup language (XML), JavaScript Object Notation (JSON), or the like, enabling processes or devices to detect categories of data.

2 FIG. 204 204 204 204 204 200 Alternatively or additionally, and continuing to refer to, training datamay include one or more elements that are not categorized; that is, training datamay not be formatted or contain descriptors for some elements of data. Machine-learning algorithms and/or other processes may sort training dataaccording to one or more categorizations using, for instance, natural language processing algorithms, tokenization, detection of correlated values in raw data and the like; categories may be generated using correlation and/or other processing algorithms. As a non-limiting example, in a corpus of text, phrases making up a number “n” of compound words, such as nouns modified by other nouns, may be identified according to a statistically significant prevalence of n-grams containing such words in a particular order; such an n-gram may be categorized as an element of language such as a “word” to be tracked similarly to single words, generating a new category as a result of statistical analysis. Similarly, in a data entry including some textual data, a person's name may be identified by reference to a list, dictionary, or other compendium of terms, permitting ad-hoc categorization by machine-learning algorithms, and/or automated association of data in the data entry with descriptors or into a given format. The ability to categorize data entries automatedly may enable the same training datato be made applicable for two or more distinct machine-learning algorithms as described in further detail below. Training dataused by machine-learning modulemay correlate any input data as described in this disclosure to any output data as described in this disclosure.

2 FIG. 216 216 200 204 Further referring to, training data may be filtered, sorted, and/or selected using one or more supervised and/or unsupervised machine-learning processes and/or models as described in further detail below; such models may include without limitation a training data classifier. Training data classifiermay include a “classifier generated by a machine learning algorithm known as a “classification algorithm”. Machine-learning modulemay generate a classifier using a classification algorithm, defined as a processes whereby a computing device and/or any module and/or component operating thereon derives a classifier from training data.

2 FIG. 200 220 204 204 Still referring to, machine-learning modulemay be configured to perform a lazy-learning processand/or protocol, which may alternatively be referred to as a “lazy loading” or “call-when-needed” process and/or protocol, may be a process whereby machine learning is conducted upon receipt of an input to be converted to an output, by combining the input and training set to derive the algorithm to be used to produce the output on demand. For instance, an initial set of simulations may be performed to cover an initial heuristic and/or “first guess” at an output and/or relationship. As a non-limiting example, an initial heuristic may include a ranking of associations between inputs and elements of training data. Heuristic may include selecting some number of highest-ranking associations and/or training dataelements. Lazy learning may implement any suitable lazy learning algorithm, including without limitation a K-nearest neighbors algorithm, a lazy naïve Bayes algorithm, or the like; persons skilled in the art, upon reviewing the entirety of this disclosure, will be aware of various lazy-learning algorithms that may be applied to generate outputs as described in this disclosure, including without limitation lazy learning applications of machine-learning algorithms as described in further detail below.

2 FIG. 224 224 224 204 Alternatively or additionally, and with continued reference to, machine-learning processes as described in this disclosure may be used to generate machine-learning models. A “machine-learning model,” as used in this disclosure, is a mathematical and/or algorithmic representation of a relationship between inputs and outputs, as generated using any machine-learning process including without limitation any process as described above, and stored in memory; an input is submitted to a machine-learning modelonce created, which generates an output based on the relationship that was derived. For instance, and without limitation, a linear regression model, generated using a linear regression algorithm, may compute a linear combination of input data using coefficients derived during machine-learning processes to calculate an output datum. As a further non-limiting example, a machine-learning modelmay be generated by creating an artificial neural network, such as a convolutional neural network comprising an input layer of nodes, one or more intermediate layers, and an output layer of nodes. Connections between nodes may be created via the process of “training” the network, in which elements from a training dataset are applied to the input nodes, a suitable training algorithm (such as Levenberg-Marquardt, conjugate gradient, simulated annealing, or other algorithms) is then used to adjust the connections and weights between nodes in adjacent layers of the neural network to produce the desired values at the output nodes. This process is sometimes referred to as deep learning.

2 FIG. 228 228 204 228 Still referring to, machine-learning algorithms may include at least a supervised machine-learning process. At least a supervised machine-learning process, as defined herein, include algorithms that receive a training set relating a number of inputs to a number of outputs, and seek to find one or more mathematical relations relating inputs to outputs, where each of the one or more mathematical relations is optimal according to some criterion specified to the algorithm using some scoring function. For instance, a supervised learning algorithm may include any inputs and outputs described throughout this disclosure, and a scoring function representing a desired form of relationship to be detected between inputs and outputs; scoring function may, for instance, seek to maximize the probability that a given input and/or combination of elements inputs is associated with a given output to minimize the probability that a given input is not associated with a given output. Scoring function may be expressed as a risk function representing an “expected loss” of an algorithm relating inputs to outputs, where loss is computed as an error function representing a degree to which a prediction generated by the relation is incorrect when compared to a given input-output pair provided in training data. Persons skilled in the art, upon reviewing the entirety of this disclosure, will be aware of various possible variations of at least a supervised machine-learning processthat may be used to determine relation between inputs and outputs. Supervised machine-learning processes may include classification algorithms as defined above.

2 FIG. 232 Further referring to, machine learning processes may include at least an unsupervised machine-learning processes. An unsupervised machine-learning process, as used herein, is a process that derives inferences in datasets without regard to labels; as a result, an unsupervised machine-learning process may be free to discover any structure, relationship, and/or correlation provided in the data. Unsupervised processes may not require a response variable; unsupervised processes may be used to find interesting patterns and/or inferences between variables, to determine a degree of correlation between two or more variables, or the like.

2 FIG. 200 224 Still referring to, machine-learning modulemay be designed and configured to create a machine-learning modelusing techniques for development of linear regression models. Linear regression models may include ordinary least squares regression, which aims to minimize the square of the difference between predicted outcomes and actual outcomes according to an appropriate norm for measuring such a difference (e.g., a vector-space distance norm); coefficients of the resulting linear equation may be modified to improve minimization. Linear regression models may include ridge regression methods, where the function to be minimized includes the least-squares function plus term multiplying the square of each coefficient by a scalar amount to penalize large coefficients. Linear regression models may include least absolute shrinkage and selection operator (LASSO) models, in which ridge regression is combined with multiplying the least-squares term by a factor of 1 divided by double the number of samples. Linear regression models may include a multi-task lasso model wherein the norm applied in the least-squares term of the lasso model is the Frobenius norm amounting to the square root of the sum of squares of all terms. Linear regression models may include the elastic net model, a multi-task elastic net model, a least angle regression model, a LARS lasso model, an orthogonal matching pursuit model, a Bayesian regression model, a logistic regression model, a stochastic gradient descent model, a perceptron model, a passive aggressive algorithm, a robustness regression model, a Huber regression model, or any other suitable model that may occur to persons skilled in the art upon reviewing the entirety of this disclosure. Linear regression models may be generalized in an embodiment to polynomial regression models, whereby a polynomial equation (e.g., a quadratic, cubic or higher-order equation) providing a best predicted output/actual output fit is sought; similar methods to those described above may be applied to minimize error functions, as will be apparent to persons skilled in the art upon reviewing the entirety of this disclosure.

2 FIG. Continuing to refer to, machine-learning algorithms may include, without limitation, linear discriminant analysis. Machine-learning algorithm may include quadratic discriminate analysis. Machine-learning algorithms may include kernel ridge regression. Machine-learning algorithms may include support vector machines, including, without limitation, support vector classification-based regression processes. Machine-learning algorithms may include stochastic gradient descent algorithms, including classification and regression algorithms based on stochastic gradient descent. Machine-learning algorithms may include nearest neighbors algorithms. Machine-learning algorithms may include various forms of latent space regularization such as variational regularization. Machine-learning algorithms may include Gaussian processes such as Gaussian Process Regression. Machine-learning algorithms may include cross-decomposition algorithms, including partial least squares and/or canonical correlation analysis. Machine-learning algorithms may include naïve Bayes methods. Machine-learning algorithms may include algorithms based on decision trees, such as decision tree classification or regression algorithms. Machine-learning algorithms may include ensemble methods such as bagging meta-estimator, forest of randomized tress, AdaBoost, gradient tree boosting, and/or voting classifier methods. Machine-learning algorithms may include neural net algorithms, including convolutional neural net processes.

3 FIG. 300 300 Referring now to, an exemplary embodiment of neural networkis illustrated. A neural networkalso known as an artificial neural network, is a network of “nodes,” or data structures having one or more inputs, one or more outputs, and a function determining outputs based on inputs. Such nodes may be organized in a network, such as without limitation a convolutional neural network, including an input layer of nodes, one or more intermediate layers, and an output layer of nodes. Connections between nodes may be created via the process of “training” the network, in which elements from a training dataset are applied to the input nodes, a suitable training algorithm (such as Levenberg-Marquardt, conjugate gradient, simulated annealing, or other algorithms) is then used to adjust the connections and weights between nodes in adjacent layers of the neural network to produce the desired values at the output nodes. This process is sometimes referred to as deep learning. Connections may run solely from input nodes toward output nodes in a “feed-forward” network or may feed outputs of one layer back to inputs of the same or a different layer in a “recurrent network.”

4 FIG. i i i i i i Referring now to, an exemplary embodiment of a node of a neural network is illustrated. A node may include, without limitation, a plurality of inputs xthat may receive numerical values from inputs to a neural network containing the node and/or from other nodes. Node may perform a weighted sum of inputs using weights wthat are multiplied by respective inputs x. Additionally, or alternatively, a bias b may be added to the weighted sum of the inputs such that an offset is added to each unit in the neural network layer that is independent of the input to the layer. The weighted sum may then be input into a function q, which may generate one or more outputs y. Weight wapplied to an input xmay indicate whether the input is “excitatory,” indicating that it has strong influence on the one or more outputs y, for instance by the corresponding weight having a large numerical value, and/or a “inhibitory,” indicating it has a weak effect influence on the one more inputs y, for instance by the corresponding weight having a small numerical value. The values of weights wmay be determined by training a neural network using training data, which may be performed using any suitable process as described above.

5 FIG. 500 124 120 500 140 140 116 500 140 148 500 140 136 140 148 140 148 Referring now to, an exemplary embodiment of a GUIfor importing content datafrom data fileis illustrated. GUImay present a plurality of desired data headers(i.e., “Person,” “Date,” and “Cause” in separate boxes (i.e., rows or columns), wherein each desired data headeris related to a content category. GUImay present desired data headersrequired in the generation of article. In some embodiments, GUImay confirm desired data headersto be used in article by clicking of each box. Clicking on box may induce a check mark or highlight demonstrating user selections. In some embodiments, each box may present the corresponding desired dataunder desired data headeras matched by matching machine-learning model (i.e., “John Doe” matched to “Person,” “5-Nov-2” matched to “Date,” and “Stupidity” matched to “Cause”). Each box may be edited through textual submission. For example, desired data may be re-written or submitted by a user through a text box. In some embodiments, boxes not selected may be grayed out to show distinctions. In some embodiments, additional boxes may be added by user input through menu selection. For example, a menu may present a plurality of headers that mat be imported that a user may select to add to the importation process. In some embodiments, each box may be displayed in order of implantation into article. For example, an arrangement of desired data headersof “person,” may come before “date,” and “cause.” Articlemay read in order of the name of the person, date of death, and cause of death. A user may prioritize the order of boxes black click and drag function, and the like.

6 FIG. 600 604 608 604 604 604 604 604 604 604 604 604 600 Referring now to, an exemplary embodiment of an apparatusfor generating a report is illustrated. Apparatus includes a processorand a memorycommunicatively connected to the processor. Processormay include any computing device as described in this disclosure, including without limitation a microcontroller, microprocessor, digital signal processor (DSP) and/or system on a chip (SoC) as described in this disclosure. Computing device may include, be included in, and/or communicate with a mobile device such as a mobile telephone or smartphone. Processormay include a single computing device operating independently, or may include two or more computing device operating in concert, in parallel, sequentially or the like; two or more computing devices may be included together in a single computing device or in two or more computing devices. Processormay interface or communicate with one or more additional devices as described below in further detail via a network interface device. Network interface device may be utilized for connecting processorto one or more of a variety of networks, and one or more devices. Examples of a network interface device include, but are not limited to, a network interface card (e.g., a mobile network interface card, a LAN card), a modem, and any combination thereof. Examples of a network include, but are not limited to, a wide area network (e.g., the Internet, an enterprise network), a local area network (e.g., a network associated with an office, a building, a campus or other relatively small geographic space), a telephone network, a data network associated with a telephone/voice provider (e.g., a mobile communications provider data and/or voice network), a direct connection between two computing devices, and any combinations thereof. A network may employ a wired and/or a wireless mode of communication. In general, any network topology may be used. Information (e.g., data, software etc.) may be communicated to and/or from a computer and/or a computing device. Processormay include but is not limited to, for example, a computing device or cluster of computing devices in a first location and a second computing device or cluster of computing devices in a second location. Processormay include one or more computing devices dedicated to data storage, security, distribution of traffic for load balancing, and the like. Processormay distribute one or more computing tasks as described below across a plurality of computing devices of computing device, which may operate in parallel, in series, redundantly, or in any other manner used for distribution of tasks or memory between computing devices. Processormay be implemented using a “shared nothing” architecture in which data is cached at the worker, in an embodiment, this may enable scalability of apparatusand/or computing device.

6 FIG. 604 604 604 With continued reference to, processormay be designed and/or configured to perform any method, method step, or sequence of method steps in any embodiment described in this disclosure, in any order and with any degree of repetition. For instance, processormay be configured to perform a single step or sequence repeatedly until a desired or commanded outcome is achieved; repetition of a step or a sequence of steps may be performed iteratively and/or recursively using outputs of previous repetitions as inputs to subsequent repetitions, aggregating inputs and/or outputs of repetitions to produce an aggregate result, reduction or decrement of one or more variables such as global variables, and/or division of a larger processing task into a set of iteratively addressed smaller processing tasks. Processormay perform any step or sequence of steps as described in this disclosure in parallel, such as simultaneously and/or substantially simultaneously performing a step two or more times using two or more parallel threads, processor cores, or the like; division of tasks between parallel threads and/or processes may be performed according to any protocol suitable for division of tasks between iterations. Persons skilled in the art, upon reviewing the entirety of this disclosure, will be aware of various ways in which steps, sequences of steps, processing tasks, and/or data may be subdivided, shared, or otherwise dealt with using iteration, recursion, and/or parallel processing.

6 FIG. With continued reference to, as used in this disclosure, “communicatively connected” means connected by way of a connection, attachment, or linkage between two or more relata which allows for reception and/or transmittance of information therebetween. For example, and without limitation, this connection may be wired or wireless, direct, or indirect, and between two or more components, circuits, devices, systems, apparatus and the like, which allows for reception and/or transmittance of data and/or signal(s) therebetween. Data and/or signals therebetween may include, without limitation, electrical, electromagnetic, magnetic, video, audio, radio and microwave data and/or signals, combinations thereof, and the like, among others. A communicative connection may be achieved, for example and without limitation, through wired or wireless electronic, digital or analog, communication, either directly or by way of one or more intervening devices or components. Further, communicative connection may include electrically coupling or connecting at least an output of one device, component, or circuit to at least an input of another device, component, or circuit. For example, and without limitation, via a bus or other facility for intercommunication between elements of a computing device. Communicative connecting may also include indirect connections via, for example and without limitation, wireless connection, radio communication, low power wide area network, optical communication, magnetic, capacitive, or optical coupling, and the like. In some instances, the terminology “communicatively coupled” may be used in place of communicatively connected in this disclosure.

6 FIG. 604 612 616 With continued reference to, processoris configured to receive structured datafrom structured data source. For the purposes of this disclosure, “structured data” is data that has been organized into a standardized format. For the purposes of this disclosure, a “structured data source,” is a data source that holds structured data.

6 FIG. 612 612 612 612 612 612 With continued reference to, structured datamay include information regarding noteworthy events. Structured datamay include information regarding one or more of financial events, management events, newsworthy events, and the like. Structured datamay include information from news reports, social media posts, police reports, user inputs, and the like. Structured datamay describe the parties involved, locations, times, detailed accounts of the events, and the like. Financial events can encompass a wide range of occurrences within the financial world, such as market movements, economic reports, corporate actions, policy changes, and more. These events can be local, regional, or global in scope and may have positive or negative consequences for various stakeholders. Examples of financial events may include economic indicators, corporate earnings reports, central bank actions, mergers and acquisitions, political events, natural disasters, stock market crashes, global events, and the like. Structured dataassociated with financial events may outline a detailed accounting of the event. Structured datamay also include information regarding who will be affected by the financial event and whether this event is positive or negative. A newsworthy event is any occurrence or happening that is of significant interest, importance, or relevance to the public and has the potential to be reported and covered by news media outlets. Newsworthy events may also include events that are noteworthy to certain demographic groups. These events often have a widespread impact on society, communities, or individuals and can include a wide range of topics, such as politics, economics, science, technology, social issues, entertainment, and sports.

6 FIG. 620 612 620 620 620 620 With continued reference to, as used in this disclosure, “receive” means accepting, collecting, or otherwise receiving input from activity data source described in further detail below. As used in this disclosure, “activity data” is structured data concerning an activity. As used in this disclosure, an “activity” is an event, phenomena, or occurrence that is noteworthy or newsworthy. In a non-limiting example, activity data may include data regarding sporting events. An activity may include scored event that one or more people may partake in. In some cases, sporting event may include, without limitation, football, basketball, car racing, Olympic sports, soccer, volleyball, baseball, softball, cricket, darts, bowling, and the like thereof. In another non-limiting example, activity data may include data regarding to a gaming event. In some cases, gaming event may include chess, darts, cards, multiplayer video games, and the like thereof. In a non-limiting example, activity data may include, without limitation, game details, team information, player information, time duration, and the like thereof. In another non-limiting example, activity data may include a minute-by-minute sporting event commentary script. In some embodiments, activity data may include a box score. In some embodiments, structured datamay include a box score. As used in this disclosure, a “box score” is a structured summary of results from a sporting event or activity. In some embodiments, box scoremay break the activity data into temporal divisions of the sporting event, such as, without limitation, quarters, halves, periods, frames, innings, sets, and the like thereof. In a non-limiting example, a box scoremay include a data element similar to “Team A x: Team B y,” wherein the data element may compare team A score x to team B score y. In some embodiments, the score may be the points scored by the end of a temporal division. In some embodiments, the score may be the points scored during a temporal division. In some embodiments, box scoremay include a list of events. List of events may include, for example, a list of the scoring events or other significant events, such as penalties, injuries, turnovers, and the like.

6 FIG. 612 624 612 624 624 612 612 612 624 624 620 624 624 624 624 612 624 624 612 With continued reference to, in some embodiments, structured dataor activity data may further include a confidence score. As used in this disclosure, a “confidence score” is a quantitative measurement of the accuracy of the data such as, without limitation, structured data. Confidence scoremay be on a scale of x to y, wherein x may represent a minimum confidence score and y may represent a maximum confidence score; for instance, confidence scoremay be on a scale of 0 to 100, wherein a confidence score close to 0 may be a low confidence score, and a confidence score close to 100 may be a high confidence score. Low confidence score may indicate structured datais less reliable, while high confidence score may indicate structured datais more reliable. In some embodiments, structured datamay include a plurality of confidence scores, wherein each confidence score of plurality of confidence scoresmay associate with a single box score. In a non-limiting example, a confidence scoremay be generated by comparing two or more news reports, police reports, or social media posts to one another. If the facts associated with each report are aligned the confidence scoremay be high, alternatively if the facts from each report are varied the confidence score may be low. An overall confidence score may be calculated, generated, or determined as a function of plurality of confidence scores. Additionally, or alternatively, confidence scoremay be a user-defined score. In a non-limiting example, a user may review structured dataand determine one or more confidence scorebased on the user's intuition. In other embodiments, confidence scoremay be obtained from or received along with structured datafrom activity data source described in further detail below.

6 FIG. 612 With continued reference to, in some embodiments, structured dataand/or any data/information described in this disclosure may be present as a vector. As used in this disclosure, a “vector” is a data structure that represents one or more quantitative values and/or measures of home resource data. A vector may be represented as an n-tuple of values, where n is one or more values, as described in further detail below; a vector may alternatively or additionally be represented as an element of a vector space, defined as a set of mathematical objects that can be added together under an operation of addition following properties of associativity, commutativity, existence of an identity element, and existence of an inverse element for each vector, and can be multiplied by scalar values under an operation of scalar multiplication compatible with field multiplication, and that has an identity element is distributive with respect to vector addition, and is distributive with respect to field addition. Each value of n-tuple of values may represent a measurement or other quantitative value associated with a given category of data, or attribute, examples of which are provided in further detail below; a vector may be represented, without limitation, in n-dimensional space using an axis per category of value represented in n-tuple of values, such that a vector has a geometric direction characterizing the relative quantities of attributes in the n-tuple as compared to each other. Two vectors may be considered equivalent where their directions, and/or the relative quantities of values within each vector as compared to each other, are the same; thus, as a non-limiting example, a vector represented as [5, 60, 65] may be treated as equivalent, for purposes of this disclosure, as a vector represented as [6, 2, 3]. Vectors may be more similar where their directions are more similar, and more different where their directions are more divergent, for instance as measured using cosine similarity as computed using a dot product of two vectors; however, vector similarity may alternatively or additionally be determined using averages of similarities between like attributes, or any other measure of similarity suitable for any n-tuple of values, or aggregation of numerical similarity measures for the purposes of loss functions as described in further detail below. Any vectors as described herein may be scaled, such that each vector represents each attribute along an equivalent scale of values. Each vector may be “normalized,” or divided by a “length” attribute, such as a length attribute l as derived using a Pythagorean norm:

i where ais attribute number i of the vector. Scaling and/or normalization may function to make vector comparison independent of absolute quantities of attributes, while preserving any dependency on similarity of attributes.

6 FIG. 612 620 624 612 612 612 620 With continued reference to, in some embodiments, structured dataand/or any other data/information described in this disclosure may be present as a dictionary. As used in this disclosure, a “dictionary” is a data structure containing an unordered set of key value pairs. In this disclosure, a “key value pair” is a data representation of a data element such as, without limitation, entries of box score, confidence score, financial report, management report, any other information within structured y data, and the like thereof. In some cases, dictionary may be an associative memory, or associative arrays, or the like thereof. In a non-limiting example, dictionary may be a hash table. In an embodiment, key value pair may include a unique key, wherein the unique kay may associate with one or more values. In another embodiment, key value pair may include a value, wherein the value may associate with a single key. In some cases, each key value pair of set of key value pairs in dictionary may be separated by a separator, wherein the separator is an element for separating two key value pairs. In a non-limiting example, separator may be a comma in between each key value pairs of plurality of key value pairs within dictionary. In another non-limiting example, a dictionary may be expressed as “{first key value pair, second key value pair},” wherein the first key value pair and the second key value pair may be separate by a comma separator, and wherein both first key value pair and second key value pair may be expressed as “first/second key: first/second value.” In a further non-limiting example, activity datamay be present as a dictionary: “{x: A, y: B},” wherein x may be a first entry correspond to a box score A and y may be a second entry correspond to a confidence score B. Additionally, or alternatively, dictionary may include a term index, wherein the term index is a data structure to facilitate fast lookup of entries within dictionary (i.e., index). In some cases, without limitation, term index may use a zero-based indexing, wherein the zero-based indexing may configure dictionary to start with index 0. In some cases, without limitation, term index may use a one-based indexing, wherein the one-based indexing may configure dictionary to start with index 1. In other cases, without limitation, term index may use a n-based indexing, wherein the n-based indexing may configure dictionary to start with any index from 0 to n. Further, term index may be determined/calculated using one or more hash functions. As used in this disclosure, a “hash function” is a function used to map a data of arbitrary size to a fixed-size value. In some cases, a fixed-size value may include, but is not limited to, hash value, hash code, hash digest, and the like. In a non-limiting example, activity datamay be present as a dictionary containing a plurality of hashes generated using hash function such as, without limitation, identity hash function, trivial hash function, division hash function, word length folding, and the like, wherein each hash of plurality of hashes may represents a single box score.

6 FIG. 612 612 612 600 612 With continued reference to, in other embodiments, structured dataand/or any other data/information described in this disclosure may be present as any other data structure such as, without limitation, tuple, single dimension array, multi-dimension array, list, linked list, queue, set, stack, dequeue, stream, map, graph, tree, and the like thereof. In some embodiments, structured dataand/or any other data/information described in this disclosure may be present as a combination of more than one above data structures. In a non-limiting example, structured datamay include a dictionary of lists. As will be appreciated by persons having ordinary skill in the art, after having read the entirety of this disclosure, the foregoing list is provided by way of example and other data structures can be added as an extension or improvements of apparatusdisclosed herein. In some embodiments, without limitation, data structure may include an immutable data structure, wherein the immutable data structure is a data structure that cannot be changed, modified, and/or updated once data structure is initialized. In other embodiments, without limitation, data structure may include a mutable data structure, wherein the mutable data structure is a data collection that can be changed, modified, and/or updated once data structure is initialized. Additionally, or alternatively, structured dataand/or any other data/information described in this disclosure may include an electric file format such as, without limitation, txt file, JSON file, XML file, word document, pdf file, excel sheet, image, video, audio, and the like thereof.

6 FIG. 612 600 With continued reference to, in some cases, data within data structure described above may be sorted in a certain order such as, without limitation, ascending order, descending order, and the like thereof. In a non-limiting example, sorting data within structured datamay include using a sorting algorithm. In some cases, sorting algorithm may include, but is not limited to, selection sort, bubble sort, insertion sort, merge sort, quick sort, heap sort, radix sort, and the like thereof. As will be appreciated by persons having ordinary skill in the art, after having read the entirety of this disclosure, the foregoing list is provided by way of example and other sorting algorithm can be added as an extension or improvements of apparatusdisclosed herein.

6 FIG. 612 616 616 600 620 612 600 616 600 616 612 648 612 612 612 624 604 660 616 With continued reference to, as used in this disclosure, an “activity data source” is a source of structured data. An structured data sourcemay include one or more documents related to the activity. Examples of documents may include police reports, news reports, social media posts, emails, financial reports, memos, notes, quotes, and the like. In some embodiments, without limitation, structured data sourcemay include information provided from one or more users. In some cases, users may include a game player, activity organizer, application user, any individual who uses apparatus, and the like. In a non-limiting example, box scorewithin structured dataof a sporting event may be manually updated by people attending the sporting event. In some embodiments, apparatusmay receive financial data from structured data source. In some embodiments, apparatusmay receive real estate data from structured data source. In some embodiments, real estate data may include sales data. In some embodiments, real estate data may include tax assessment data. Additionally, or alternatively, structured datamay include one or more report configurations, wherein one or more report configurations are parameter used to generate structured data reportdescribed in further detail below. In some embodiments, receiving structured datamay include receiving structured datafrom the user. In a non-limiting example, user may input a plurality of structured datacontaining one or more article configurations such as, without limitation, number of authors, coverage area, confidence score, dynamic degree, and the like to processorand/or Language processing moduledescribed in further detail below. In an embodiment, an structured data sourcemay be converted into machine-encoded text using an optical character reader (OCR).

6 FIG. Still referring to, in some embodiments, optical character recognition or optical character reader (OCR) includes automatic conversion of images of written (e.g., typed, handwritten, or printed text) into machine-encoded text. In some cases, recognition of at least a keyword from an image component may include one or more processes, including without limitation optical character recognition (OCR), optical word recognition, intelligent character recognition, intelligent word recognition, and the like. In some cases, OCR may recognize written text, one glyph or character at a time. In some cases, optical word recognition may recognize written text, one word at a time, for example, for languages that use a space as a word divider. In some cases, intelligent character recognition (ICR) may recognize written text one glyph or character at a time, for instance by employing machine learning processes. In some cases, intelligent word recognition (IWR) may recognize written text, one word at a time, for instance by employing machine learning processes.

6 FIG. Still referring to, in some cases, OCR may be an “offline” process, which analyses a static document or image frame. In some cases, handwriting movement analysis can be used as input for handwriting recognition. For example, instead of merely using shapes of glyphs and words, this technique may capture motions, such as the order in which segments are drawn, the direction, and the pattern of putting the pen down and lifting it. This additional information can make handwriting recognition more accurate. In some cases, this technology may be referred to as “online” character recognition, dynamic character recognition, real-time character recognition, and intelligent character recognition.

6 FIG. Still referring to, in some cases, OCR processes may employ pre-processing of image components. Pre-processing process may include without limitation de-skew, de-speckle, binarization, line removal, layout analysis or “zoning,” line and word detection, script recognition, character isolation or “segmentation,” and normalization. In some cases, a de-skew process may include applying a transform (e.g., homography or affine transform) to the image component to align text. In some cases, a de-speckle process may include removing positive and negative spots and/or smoothing edges. In some cases, a binarization process may include converting an image from color or greyscale to black-and-white (i.e., a binary image). Binarization may be performed as a simple way of separating text (or any other desired image component) from the background of the image component. In some cases, binarization may be required for example if an employed OCR algorithm only works on binary images. In some cases. a line removal process may include the removal of non-glyph or non-character imagery (e.g., boxes and lines). In some cases, a layout analysis or “zoning” process may identify columns, paragraphs, captions, and the like as distinct blocks. In some cases, a line and word detection process may establish a baseline for word and character shapes and separate words, if necessary. In some cases, a script recognition process may, for example in multilingual documents, identify a script allowing an appropriate OCR algorithm to be selected. In some cases, a character isolation or “segmentation” process may separate signal characters, for example, character-based OCR algorithms. In some cases, a normalization process may normalize the aspect ratio and/or scale of the image component.

6 FIG. Still referring to, in some embodiments, an OCR process will include an OCR algorithm. Exemplary OCR algorithms include matrix-matching process and/or feature extraction processes. Matrix matching may involve comparing an image to a stored glyph on a pixel-by-pixel basis. In some cases, matrix matching may also be known as “pattern matching,” “pattern recognition,” and/or “image correlation.” Matrix matching may rely on an input glyph being correctly isolated from the rest of the image component. Matrix matching may also rely on a stored glyph being in a similar font and at the same scale as input glyph. Matrix matching may work best with typewritten text.

6 FIG. 5 7 FIGS.- Still referring to, in some embodiments, an OCR process may include a feature extraction process. In some cases, feature extraction may decompose a glyph into features. Exemplary non-limiting features may include corners, edges, lines, closed loops, line direction, line intersections, and the like. In some cases, feature extraction may reduce dimensionality of representation and may make the recognition process computationally more efficient. In some cases, extracted features can be compared with an abstract vector-like representation of a character, which might reduce to one or more glyph prototypes. General techniques of feature detection in computer vision are applicable to this type of OCR. In some embodiments, machine-learning processes like nearest neighbor classifiers (e.g., k-nearest neighbors algorithm) can be used to compare image features with stored glyph features and choose a nearest match. OCR may employ any machine-learning process described in this disclosure, for example machine-learning processes described with reference to. Exemplary non-limiting OCR software includes Cuneiform and Tesseract. Cuneiform is a multi-language, open-source optical character recognition system originally developed by Cognitive Technologies of Moscow, Russia. Tesseract is free OCR software originally developed by Hewlett-Packard of Palo Alto, California, United States.

6 FIG. 2 3 4 FIGS.,, and Still referring to, in some cases, OCR may employ a two-pass approach to character recognition. The second pass may include adaptive recognition and use letter shapes recognized with high confidence on a first pass to recognize better remaining letters on the second pass. In some cases, two-pass approach may be advantageous for unusual fonts or low-quality image components where visual verbal content may be distorted. Another exemplary OCR software tool include OCRopus. OCRopus development is led by German Research Centre for Artificial Intelligence in Kaiserslautern, Germany. In some cases, OCR software may employ neural networks, for example neural networks as taught in reference to.

6 FIG. Still referring to, in some cases, OCR may include post-processing. For example, OCR accuracy can be increased, in some cases, if output is constrained by a lexicon. A lexicon may include a list or set of words that are allowed to occur in a document. In some cases, a lexicon may include, for instance, all the words in the English language, or a more technical lexicon for a specific field. In some cases, an output stream may be a plain text stream or file of characters. In some cases, an OCR process may preserve an original layout of visual verbal content. In some cases, near-neighbor analysis can make use of co-occurrence frequencies to correct errors, by noting that certain words are often seen together. For example, “Washington, D.C.” is generally far more common in English than “Washington DOC.” In some cases, an OCR process may make use of a priori knowledge of grammar for a language being recognized. For example, grammar rules may be used to help determine if a word is likely to be a verb or a noun. Distance conceptualization may be employed for recognition and classification. For example, a Levenshtein distance algorithm may be used in OCR post-processing to further optimize results.

6 FIG. 616 612 604 612 616 604 600 612 With continued reference to, in some embodiments, structured data sourcemay include a data store such as, without limitation, a database. Database may be implemented, without limitation, as a relational database, a key-value retrieval database such as a NOSQL database, or any other format or structure for use as a database that a person skilled in the art would recognize as suitable upon review of the entirety of this disclosure. Database may alternatively or additionally be implemented using a distributed data storage protocol and/or data structure, such as a distributed hash table or the like. Database may include a plurality of data entries and/or records as described above. Data entries in a database may be flagged with or linked to one or more additional elements of information, which may be reflected in data entry cells and/or in linked tables such as tables related by one or more indices in a relational database. Persons skilled in the art, upon reviewing the entirety of this disclosure, will be aware of various ways in which data entries in a database may store, retrieve, organize, and/or reflect data and/or records as used herein, as well as categories and/or populations of data consistently with this disclosure. In a non-limiting example, a scheduler may store structured dataat a specified time after event ends in database. Processormay be configured to access database and/or retrieve structured datawithin database through one or more database queries. In other embodiments, structured data sourcemay include one or more application program interface (API), wherein the application programming interface is a way for two or more devices and or programs to communicate with each other. In a non-limiting example, processorwithin apparatusmay be configured to fetch structured datathrough sport data feed application programming interface at a specific endpoint.

6 FIG. 604 628 612 628 628 628 628 628 628 628 632 612 632 628 632 612 620 628 With continued reference to, processoris further configured to determine an activity classificationas a function of structured data. As used in this disclosure, an “activity classification” is a type of an activity. The activity may include, without limitation, sporting events described above. In a non-limiting example, activity classificationmay include “blowout victory,” “come-from-behind win,” “huge loss,” “close game,” “overtime thriller,” and/or the like. An activity classificationmay include classifying the activity as a “financial activity,” “managerial activity,” “sports activity,” “political activity” “newsworthy activity,” and the like. Activity classificationmay include “unprofitable quarter,” “profitable quarter,” “good year-over-year growth,” and the like. Activity classificationmay include “ineffective employee,” “understaffed company,” and the like. Activity classificationmay include “prices increasing,” “prices holding steady,” “buyer's market,” “seller's market,” and the like. An activity classificationmay additionally classify the activity according to the people, entities, organizations, and the like that are involved with the activity. In some embodiments, determining activity classificationmay include applying a plurality of activity conditionsto structured data. As used in this disclosure an “activity condition” is a circumstance affecting the activity. In a non-limiting example, activity conditionmay include one or more circumstance that affect an activity to fall into one or more categories such as, without limitation, activity classificationdescribed above. In some embodiments, activity conditionmay use structured datathat is broken into temporal divisions, such as box score, days, weeks, hours, etc., to determine activity classification.

6 FIG. 628 With continued reference to, an activity classificationmay include an activity identifier. As used in the current disclosure, an “activity identifier” is an identification of one or more key facts related to the activity. Key facts in an activity may refer to essential pieces of information that provide a concise and relevant summary of the activity. These facts are crucial for understanding the nature, scope, and outcomes of the activity. When reporting or documenting an activity, presenting key facts allows readers or stakeholders to grasp the most important aspects quickly. Key facts may include the duration, summary, outcomes, resolutions, challenges, resource utilization, and the like of the activity. Activity identifier may include identifying the date and time the activity took place, or will take place, help establish the temporal context of the activity. Additionally, the activity identifier may include an identification of a specific venue or location where the activity occurred is mentioned to understand its geographical context. An activity identifier may include identifying primary purpose or goal of the activity is stated. This may include an explanation of why the activity is significant or newsworthy to the reader. An activity identifier may include may identify the participants, individuals, groups, entities, and the like that are involved in the activity, such as team members, attendees, players, teams, companies, sporting leagues, or stakeholders, are listed. In a non-limiting example, an activity identifier may include concise summary of what happened during a financial event. This should include the primary activities or actions that occurred, such as a change in interest rates, a company's profit announcement, or a regulatory decision. In a non-limiting example, an activity identifier may include an assessment of the consequences and effects of the activity. For example, this can encompass a financial activities or newsworthy activities influence on the stock market, currency exchange rates, interest rates, consumer behavior, industry sectors, or the broader economy.

6 FIG. 604 612 612 620 632 632 612 612 620 632 632 612 628 612 604 632 612 604 604 604 604 604 604 With continued reference to, processormay receive structured dataof a football game. Structured datamay include one or more box scoresthat matches with an activity condition, wherein the activity conditionmay include “(a team) lead after every quarter and won by a certain margin.” In this circumstance, for example, structured datamay then be classified as a “blowout victory.” In another non-limiting example, structured dataregarding to a football game may include one or more box scoresthat matches with an activity condition, wherein the activity conditionmay include “(a team) was trailing after halftime but won the game.” Structured datamay then be determined as a “come-from-behind win.” In some embodiments, determining activity classificationmay include applying a first set of activity conditions to structured dataand applying a second set of activity conditions to activity data, wherein the first set of activity conditions is a subset of the second set of activity conditions. In a non-limiting example, processormay apply plurality of activity conditionsto structured datafrom most restrictive circumstances to least restrictive circumstances; for instance, processormay first check whether there is a match with circumstances of “overtime game.” Processormay then check whether there is a match with circumstances of “comeback win.” Processormay finally check whether there is a match with circumstances of “normal game.” For instance, processormay first check whether there is a match with circumstances of “good year-over-year growth.” Processormay then check whether there is a match with circumstances of “unprofitable quarter.” Processormay finally check whether there is a match with circumstances of “profitable quarter.”

6 FIG. 8 FIG. 628 632 628 612 632 632 612 632 612 628 612 628 628 With continued reference to, in some embodiments, determining activity classificationmay include a use of a rule-based engine. As used in this disclosure, a “rule-based engine” is a system that executes one or more rules in a runtime production environment. As used in this disclosure, a “rule” is a pair including a set of conditions and a set of actions, wherein each condition within the set of conditions is a representation of a fact, an antecedent, or otherwise a pattern, and each action within the set of actions is a representation of a consequent. In a non-limiting example, rule may include a condition such as, without limitation, activity conditionof “(a team) did not score for the whole game” pair with a consequent such as, without limitation, activity classificationof “huge loss.” In some embodiments, rule-based engine may execute one or more rules on structured dataif any activity conditionsare met. In some embodiments, rule-based engine may include an inference engine for determine a match of activity condition, where any or all structured datamay be represented as values and/or fuzzy sets for linguistic variables measuring the same, as described in more detail in. Inference engine may use one or more fuzzy inferencing rules to output one or more linguistic variable values and/or defuzzified values indicating match of activity condition. As used in the current disclosure, a “fuzzy inference” is a method that interprets the values in the input vector (i.e., structured data, activity classification.) and, based on a set of rules, assigns values to the output vector. A fuzzy set may also be used to show degree of match between fuzzy sets may be used to rank one resource against another. For instance, if both excessive structured dataand activity classificationhave fuzzy sets, activity classificationmay be determined by having a degree of overlap exceeding a predetermined threshold.

6 FIG. 604 628 612 632 632 628 604 612 632 632 628 604 628 612 632 628 With continued reference to, processormay determine activity classificationusing a using a lookup table. A “lookup table,” for the purposes of this disclosure, is an array of data that maps input values to output values. A lookup table may be used to replace a runtime computation with an array indexing operation. A look-up table may be configured to pre-calculate and store data in static program storage, calculated as part of a program's initialization phase, or even stored in hardware in application-specific platforms. In another non limiting example, an activity classification lookup table may be able to correlate structured datato an activity conditionand further correlate the activity conditionto an activity classification. Processormay be configured to “lookup” structured dataand/or activity conditionin order to find a corresponding activity conditionand/or activity classification. Storing data within lookup table may allow for quick recall of data by processor. Data within the lookup table may include previous examples of plurality of activity classificationscompared to structured dataand/or activity condition. Data within the lookup table may be received from a database. Lookup tables may also be used to identify activity classificationsby matching an input value to an output value by matching the input against a list of valid (or invalid) items in an array.

6 FIG. 604 628 With continued reference to, in some embodiments, processormay be configured to determine activity classificationusing a machine-learning model, such as a classifier. In some embodiments, the machine-learning model may be generated using a machine-learning module as described throughout this disclosure. In some embodiments, machine-learning model may be trained using categorization training data comprising exemplary structured data correlated to activity classifications. In some embodiments, the categorization training data may include exemplary articles correlated to activity classifications. In some embodiments, the structured data and/or exemplary articles in classification training data may be automatically retrieved from scaping the internet. This may allow for the acquisition of large sets of training data relatively cheaply. In some embodiments, the machine-learning model for determining an activity classification may include a clustering model. The machine-learning model may be consistent with any machine-learning model disclosed in this disclosure.

6 FIG. 628 636 604 636 636 640 640 612 628 640 616 640 612 604 628 636 636 628 612 With continued reference to, in some embodiments, determining activity classificationmay include training a classification machine-learning process. A “machine-learning process,” as used in this disclosure, is a process that automatedly uses a body of data known as training data and/or a training set (described further below in this disclosure) to generate an algorithm that will be performed by processorto produce outputs given data provided as inputs; this is in contrast to a non-machine learning software program where the commands to be executed are determined in advance by a user and written in a programming language. Classification machine-learning processmay utilize supervised, unsupervised, lazy-learning processes and/or neural networks, described further below. Classification machine-learning processmay be trained using classification training data, wherein the classification training datamay include a plurality of structured dataas input correlated to a plurality of activity classifications. In an embodiment, classification training datamay be obtained from activity data sourcedescribed above. In another embodiments, classification training datamay include manually labeled data. As a non-limiting example, structured datamay be manually collected and labeled by the user and/or a professional such as, without limitation, player, activity organizer, anyone who participates in the activity, and the like thereof. Processormay then determine activity classificationas a function of trained classification machine-learning process. In some embodiments, classification machine-learning processmay be used to determine activity classificationbased on input containing structured data; this may be performed using, without limitation, classification. In some cases, classification may be performed using, without limitation, linear classifiers such as without limitation logistic regression and/or naive Bayes classifiers, nearest neighbor classifiers such as k-nearest neighbors classifiers, support vector machines, least squares support vector machines, fisher's linear discriminant, quadratic classifiers, decision trees, boosted trees, random forest classifiers, learning vector quantization, and/or neural network-based classifiers.

6 FIG. 604 604 With continued reference to, as used in this disclosure, a “classifier” is a machine-learning model, such as a mathematical model, neural net, or program generated by a machine learning algorithm known as a “classification algorithm,” as described in further detail below, that sort inputs into categories or bins of data, outputting the categories or bins of data and/or labels associated therewith. A classifier may be configured to output at least a datum that labels or otherwise identifies a set of data that are clustered together, found to be close under a distance metric as described below, or the like. Processorand/or another device may generate a classifier using a classification algorithm, defined as a process whereby a processorderives a classifier from training data. Classification may be performed using, without limitation, linear classifiers such as without limitation logistic regression and/or naive Bayes classifiers, nearest neighbor classifiers such as k-nearest neighbors classifiers, support vector machines, least squares support vector machines, fisher's linear discriminant, quadratic classifiers, decision trees, boosted trees, random forest classifiers, learning vector quantization, and/or neural network-based classifiers.

6 FIG. 604 636 604 604 With continued reference to, in some embodiments, processormay be configured to generate machine learning model such as, without limitation, classification machine-learning process, using a Naïve Bayes classification algorithm. Naïve Bayes classification algorithm generates classifiers by assigning class labels to problem instances, represented as vectors of element values. Class labels are drawn from a finite set. Naïve Bayes classification algorithm may include generating a family of algorithms that assume that the value of a particular element is independent of the value of any other element, given a class variable. Naïve Bayes classification algorithm may be based on Bayes Theorem expressed as P(A/B)=P(B/A) P(A)÷P(B), where P(A/B) is the probability of hypothesis A given data B also known as posterior probability; P(B/A) is the probability of data B given that the hypothesis A was true; P(A) is the probability of hypothesis A being true regardless of data also known as prior probability of A; and P(B) is the probability of the data regardless of the hypothesis. A naïve Bayes algorithm may be generated by first transforming training data into a frequency table. Processormay then calculate a likelihood table by calculating probabilities of different data entries and classification labels. Processormay utilize a naïve Bayes equation to calculate a posterior probability for each class. A class containing the highest posterior probability is the outcome of prediction. Naïve Bayes classification algorithm may include a gaussian model that follows a normal distribution. Naïve Bayes classification algorithm may include a multinomial model that is used for discrete counts. Naïve Bayes classification algorithm may include a Bernoulli model that may be utilized when vectors are binary.

6 FIG. 604 636 With continued reference to, in some embodiments, processormay be configured to generate machine learning model such as, without limitation, classification machine-learning process, using a K-nearest neighbors (KNN) algorithm. A “K-nearest neighbors algorithm” as used in this disclosure, includes a classification method that utilizes feature similarity to analyze how closely out-of-sample-features resemble training data to classify input data to one or more clusters and/or categories of features as represented in training data; this may be performed by representing both training data and input data in vector forms, and using one or more measures of vector similarity to identify classifications within training data, and to determine a classification of input data. K-nearest neighbors algorithm may include specifying a K-value, or a number directing the classifier to select the k most similar entries training data to a given sample, determining the most common classifier of the entries in the database, and classifying the known sample; this may be performed recursively and/or iteratively to generate a classifier that may be used to classify input data as further samples. For instance, an initial set of samples may be performed to cover an initial heuristic and/or “first guess” at an output and/or relationship, which may be seeded, without limitation, using expert input received according to any process as described herein. As a non-limiting example, an initial heuristic may include a ranking of associations between inputs and elements of training data. Heuristic may include selecting some number of highest-ranking associations and/or training data elements.

6 FIG. i With continued reference to, generating k-nearest neighbors algorithm may generate a first vector output containing a data entry cluster, generating a second vector output containing an input data, and calculate the distance between the first vector output and the second vector output using any suitable norm such as cosine similarity, Euclidean distance measurement, or the like. Each vector output may be represented, without limitation, as an n-tuple of values, where n is at least two values. Each value of n-tuple of values may represent a measurement or other quantitative value associated with a given category of data, or attribute, examples of which are provided in further detail below; a vector may be represented, without limitation, in n-dimensional space using an axis per category of value represented in n-tuple of values, such that a vector has a geometric direction characterizing the relative quantities of attributes in the n-tuple as compared to each other. Two vectors may be considered equivalent where their directions, and/or the relative quantities of values within each vector as compared to each other, are the same; thus, as a non-limiting example, a vector represented as [5, 60, 65] may be treated as equivalent, for purposes of this disclosure, as a vector represented as [6, 2, 3]. Vectors may be more similar where their directions are more similar, and more different where their directions are more divergent; however, vector similarity may alternatively or additionally be determined using averages of similarities between like attributes, or any other measure of similarity suitable for any n-tuple of values, or aggregation of numerical similarity measures for the purposes of loss functions as described in further detail below. Any vectors as described herein may be scaled, such that each vector represents each attribute along an equivalent scale of values. Each vector may be “normalized,” or divided by a “length” attribute, such as a length attribute l as derived using a Pythagorean norm, where ais attribute number experience of the vector. Scaling and/or normalization may function to make vector comparison independent of absolute quantities of attributes, while preserving any dependency on similarity of attributes; this may, for instance, be advantageous where cases represented in training data are represented by different quantities of samples, which may result in proportionally equivalent vectors with divergent values.

6 FIG. 604 644 628 644 644 628 644 628 644 628 644 628 644 616 644 With continued reference to, processoris further configured to select a plurality of tokensas a function of the activity classification. As used in this disclosure, a “token” is a linguistic segment or theme associated with the activity. In a non-limiting example, tokensmay include words, phrases, sentences, themes, keyword, and the like. In some cases, tokensmay be tagged to correspond with different activity classifications. For example, a plurality of tokensmay describe keywords for financial activity. Keywords may be interest rates, depression, housing market, federal reserve. In another example, a plurality of tokens may describe themes associated with a political activity. Themes may be presidential election, democratic, republican, presidential debate, and the like. In other cases, tokens may be tagged to correspond with multiple activity classifications. In another non-limiting example, a token may include one or more themes associated with the activity. Themes may include tone (formal, informal, journalistic, scholarly, etc.), persuasiveness, fact based, opinion, and the like. In a non-limiting example, plurality of tokensmay include a first token corresponding to a first activity classification and a second token corresponds to a second activity classification. For instance, first token “got out to an early lead” may correspond to first activity classification “blowout victory.” Second token “follow closely behind” may correspond to second activity classification “close game.” More exciting adjectives and adverbs may be tagged with more exciting activity classifications. In some embodiments, selecting plurality of tokensmay include selecting one or more tokens corresponding to determined activity classificationdescribed above. Additionally, or alternatively, plurality of tokensmay be stored and/or retrieved from database described above in reference to structured data source. In a non-limiting example, selecting plurality of tokensmay include selecting plurality of tokens from a bank of content, wherein the bank of content may include a plurality of linguistic data. Bank of content may be stored in a database as described above.

6 FIG. 604 648 644 648 648 648 648 648 624 648 624 648 604 624 612 648 604 624 With continued reference to, processoris further configured to generate an structured data reportas a function of plurality of tokens. As used in this disclosure, “structured data report” is a report that is generated from a structured data source. In some embodiments, structured data reportmay include an activity report. As used in this disclosure, an “activity report” is a report describing various aspects of an activity. An activity report may include a document that provides a comprehensive summary of the activities, tasks, and/or accomplishments of an individual, team, department, or organization over a specific period of time. For example, an activity may include, without limitation, a sporting event, financial event, political event, newsworthy event, and the like as described above. Structured data reportmay be used for internal communication and management purposes to track progress, assess performance, and make informed decisions. For instance, and without limitation, structured data reportmay include, for example and without limitation, a financial report, such as an investor report for a company. In some cases, the format of the activity report may be journalistic. In some cases, structured data reportmay be in a newspaper, magazine, any other publications, and the like thereof. In some embodiments, generating structured data reportmay include comparing confidence scoreto a confidence threshold and generating structured data reportas a function of the comparison of confidence scoreand the confidence threshold. As used in this disclosure, a “confidence threshold” is a confidence score magnitude that must be exceeded for certain condition to occur or be manifested. In a non-limiting example, structured data reportmay be generated by processorif, and only if confidence scoreof activity dataexceeds confidence threshold. In another non-limiting example, structured data reportmay not be generated by processorif confidence scoreis missing or is below a confidence threshold.

6 FIG. 6 FIG. 648 644 628 648 644 628 648 612 648 612 648 648 650 648 650 648 650 644 628 648 With continued reference to, in some embodiments, structured data reportmay be generated using an LLM as described in this disclosure above. The LLM may be trained using various news reports, police reports, memos, notes, and the like. Inputs into the LLM may include the plurality of tokensand the activity classifications. Whereas the output of the LLM may be a structured data report. Training data for the LLM may include the plurality of tokensand the activity classificationsas inputs correlated to examples of activity reports. In some embodiments, LLM may receive structured dataas input and may output structured data report. In some embodiments, LLM may receive structured dataand one or more user prompts as input and may output structured data report. LLM, as described with respect to, may be trained on a diverse dataset comprising a variety of different textual documents. In some embodiments, LLM may be trained on a specific set of textual documents, corresponding to a type of structured data reportand/or final reportthat it is configured to produce. For example, LLM may be trained using sets of financial reports, sports articles, weather reports, management reports, economic reports, and the like, such that it is specifically trained to produce a particular type of structured data reportand/or final report. This may allow for more fine-tuned output from LLM because LLMs are conventionally trained on large datasets containing a wide variety of different documents. My choosing a specific set of training data, LLM may be tailored to better produce specific types of structured data reportsand/or final reports. In an embodiment, training data may include a plurality of tokensand a plurality of activity classificationscorrelated to examples of activity reports.

6 FIG. 604 650 648 648 648 648 650 648 With continued reference to, processormay generate a final reportas a function of the structured data reportor article. As used in the current disclosure, a “final report” is an structured data reportthat has been placed through a finalization process. As used in the current disclosure, a “finalization process” refers to a structured set of steps designed to enhance the quality and accuracy of the activity report or article. A finalization process may be configured to analyze the structured data reportand correct imperfections or inaccuracies in the structured data report. This process involves careful analysis and correction of any imperfections or inaccuracies present in the content. The objective is to refine the report so that it provides a clear and precise representation of the activity being described. One purpose for generating a final reportmay be to ensure that the content of the structured data reportare free from inaccuracies and over exaggerations.

6 FIG. 650 648 648 650 648 648 648 648 650 th With continued reference to, in some embodiments, final reportmay be generated using a LLM as disclosed throughout the entirety of this disclosure. As a non-limiting example, an LLM may receive structured data reportas input and may output a final report. In some embodiments, LLM may receive structured data reportand a user prompt and may output a final report. User prompt may include any additional instructions that a user has for the LLM. In some embodiments, user prompt may include “write this at an 8grade reading level,” “write this in the style of a sports reporter,” “write this in the style of the New Yorker,” and the like. Allowing the LLM to generate a final reportfrom structured data report, allows for the elimination or reduction of factual inaccuracies that are commonplace in the output of LLMs. Allowing the LLM to work from a pre-generated structured data reportmay prevent the LLM from perpetuating factual inaccuracies or errors that may be found in its training data or generated by the LLM. For example, feeding the LLM the structured data reportmay allow it to use the facts and logic present in structured data reportinstead of generating its own. This would allow a user to take advantage of the unprecedented flexibility afforded by LLMs, such as the ability to quickly generate articles in different styles, formats, and voices, while retaining control over the accuracy and reliability of the content within final report.

6 FIG. 604 648 604 With continued reference to, a finalization process for an activity report may include a series of steps and considerations taken to complete and prepare the report for distribution, presentation, or archival. This process ensures that the report is accurate, well-organized, and effectively communicates the information related to the described activity. The finalization process may include a thorough review of the content within the activity report by processor. This includes checking that all relevant information has been included, accurate data has been provided, and any objectives or outcomes of the activity have been adequately addressed. Structured data reportmay include statistical or numerical data based on one or more facts surrounding the activity. To ensure accuracy of this data processormay be configured to cross reference the data with the original sources or verifying calculations.

6 FIG. 648 644 628 644 644 648 604 648 628 648 604 648 604 648 628 648 644 648 604 644 604 648 628 648 644 With continued reference to, in some embodiments, generating structured data reportmay include arranging plurality of tokensas a function of activity classificationIn some embodiments, arranging plurality of tokensmay include placing plurality of tokensinto structured data report. In a non-limiting example, processormay be configured to generate an structured data reportof an activity according to an activity classificationof the activity. For example, structured data reportmay include “x, y, z.” Plurality of tokens may include a first set of tokens, a second set of tokens, and a third set of tokens, wherein the first set of tokens may include tokens describe the beginning of activity, wherein the second set of tokens may include tokens describe the activity in progress, and wherein the third set of tokens may include tokens describe the end of activity. Processormay then replace x in structured data reportwith first set of tokens, y with second set of tokens, and z with third set of tokens. In another non-limiting example, processormay be configured to generate an structured data reportof a sporting event with an activity classification: “overtime thriller.” Generating structured data reportmay first start by selecting a first set of tokens from plurality of tokensand placing the first set of tokens at beginning of structured data report, wherein first set of tokens may include tokens describe the overtime portion of the sporting event. Processormay then select a second set of tokens from plurality of tokensand place the second set of tokens after first set of tokens, wherein second set of tokens may include tokens describe beginning to end of the game. In other non-limiting example, processormay be configured to generate an structured data reportof a sporting event with an activity classification: “blowout victory.” Generating structured data reportmay include arranging one or more set of tokens selected from plurality of tokenschronologically; for instance, arranging one or more set of tokens from first portion of sporting event to last portion of sporting event.

6 FIG. 648 650 652 656 648 650 652 648 648 652 652 628 604 648 648 648 604 648 650 648 650 604 604 604 652 652 652 644 652 644 652 648 652 648 648 652 652 644 648 652 648 652 652 648 With continued reference to, structured data reportand/or final reportmay include an report linkand/or boilerplate data. As used in this disclosure, an “report link” is an element within a report, such as structured data reportor final report, that contains a relationship between that report and one or more other objects. In some embodiments, report linkmay include a hyperlink. As used in this disclosure, a “hyperlink” is a digital reference to data such as, without limitation, structured data report. In some cases, hyperlink may be interaction component described in further detail below. In some embodiments, generating structured data reportmay include generating an report link, wherein generating the activity linkmay include tagging report with a report tag. As used in this disclosure, an “report tag” is an identifier used to group and/or identify a group of similar activity reports. In some cases, activity reports may be similar when content such as, without limitation, team, player, activity time, and the like are same. In other cases, reports may be similar when activity classificationsare identical. Report may include a plurality of report tags. In a non-limiting example, two reports may include contents reporting a same team. Processormay be configured to tag both reports with team name as report tag. Generating report link may further include identifying a previous report as a function of report tag. As used in this disclosure, a “previous report” is an report generated and/or published before. Previous report may be generated using processing steps described in this disclosure. In some embodiments, previous report may include an report concerning one or more aspects of a previous activity related to the current activity. In some embodiments, structured data reportand/or previous report may be stored in database described above. In some cases, storing structured data reportand/or previous report may include storing them based on their report tag. This may allow for related reports to be quickly located, so that they may be linked to in a structured data report. This improves the technology of automated report or article generation by allowing for links to other media to be intelligently and quickly incorporated into the article. In some embodiments, processormay publish structured data reportand/or final reportusing a content management system (CMS). In some embodiments, after the structured data reportand/or final reportis published, processormay receive a unique identifier tied to the report. In some embodiments, processormay store that unique identifier and report tags for the report in a database. In some embodiments, processormay store that unique identifier and report tags for the report in a lookup table. Processor may retrieve the unique identifier from the database and lookup table as a function of the report tags and generate a link to the report using the unique identifier. In a non-limiting example, database may include a first table storing a first collection of reports and a second table storing a second collection of reports, wherein each report of the first collection of reports may be tagged with a first report tag and each report of the second collection of reports may be tagged with a second report tag, and wherein the first report tag is different from the second report tag. In some embodiments, previous reports may be selected from database containing at least one report with at least one identical report tag. Generating report linkmay further include generating the report link as a function of previous report. Generating report linkmay include using any processing step described in this disclosure. In a non-limiting example, generating report linkmay include selecting one or more tokensfrom previous reports and generating report linkby rearranging tokens. In another non-limiting example, generating report linkmay include summarizing previous report into a sentence using language processing module described in further detail below. Further, generating structured data reportmay further include inserting generated report linkinto the structured data report. In a non-limiting example, structured data reportmay include one or more report linksthat link to one or more articles that concerns teams or players' last games, or previous matchups between these teams and/or players. In a non-limiting example, report linksmay be embedded within a plurality of tokensof structured data report, wherein report linksmay include previous reports of the same report tag with structured data report. Inserting report linkmay include inserting report linkinto structured data reportat different position.

6 FIG. 652 648 600 600 648 600 652 With continued reference to, in some embodiments, report linkmay include an interaction component. As used in this disclosure, an “interaction component” is an element that is interactable. In a non-limiting example, users (i.e., readers) may interact with structured data reportthrough interaction component. In some cases, interaction component, may include, without limitation, button, link, image, video, audio, and the like thereof. In some embodiments, interaction component may include an event handler. As used in this disclosure, an “event handler” is an element that operates asynchronously once an event take place. In some cases, event handler may include routine, wherein the routine is a sequence of code that is intended to be called and executed repeatedly when apparatusis running. In a non-limiting example, event handler may include a callback routine, wherein the callback routine may dictate one or more action that follows event. As used in this disclosure, an “event” is an action that take place when the user interacts with apparatus, structured data report, interaction component, and/or any other components/devices that user may interact with. For example, event may include, without limitation, clicking, holding, pressing, tapping, swiping and the like thereof. In some cases, event may include a combination of a plurality of actions. In other cases, event may involve other interactive devices such as, without limitation, mouse, keyboard, display, headphone, any other interactive device that is either electrically and/or communicatively connected to apparatus, and the like thereof. In some embodiments, event handler may utilize one or more application program interface (API) such as, without limitation, web events and the like thereof. Event handler may operate any processing step described in this disclosure. In a non-limiting example, user may be able to read previous activity report by interact with interaction component within report link. User may click on interaction component and its corresponding event handler may direct user to previous activity report by open a uniform resource locator (URL) in a new tab of current window containing previous activity report.

6 FIG. 648 656 656 656 656 656 656 648 648 656 644 656 648 With continued reference to, as used in this disclosure, “boilerplate data” is data regarding to standardized text of structured data reportthat can be used repeatedly without making major changes. In some cases, boilerplate datamay be selected by the user. In a non-limiting example, boilerplate datamay be received from a client. In a non-limiting example, user may be able to customize boilerplate databy editing text within boilerplate data. In some embodiments, boilerplate datamay include, without limitation, an AI disclaimer, links to a membership service, links to a homepage, and the like thereof. In some cases, boilerplate datamay be placed at the end of structured data report. In a non-limiting example, generating structured data reportmay include inserting a boilerplate dataafter plurality of tokens. In some embodiments, boilerplate datamay include a signature of the user (i.e., author or individual who generates structured data report) and/or a copyright notice or other legal notice.

6 FIG. 2 FIG. 1 FIG. 604 648 648 612 620 624 616 632 640 644 648 648 612 628 644 648 612 620 624 616 632 640 644 648 660 With continued reference to, processormay generate structured data reportusing a report machine-learning model. As used in the current disclosure, a “report machine-learning model” is a machine-learning model that is configured to generate structured data report. report machine-learning model may be consistent with the machine-learning model described above in. Inputs to the report machine-learning model may include activity data, box score, confidence score, activity data source, activity conditions, activity training data, token, examples of structured data report, and the like. Outputs to the report machine-learning model may include structured data reporttailored to the activity data. Report training data may include a plurality of data entries containing a plurality of inputs that are correlated to a plurality of outputs for training a processor by a machine-learning process. In an embodiment, report training data may include a plurality of activity classificationsand tokenscorrelated to examples of activity reports. Report training data may be received from a database. Report training data may contain information about activity data, box score, confidence score, activity data source, activity conditions, activity training data, token, examples of structured data report, and the like. In an embodiment, report training data may be iteratively updated as a function of the input and output results of past report machine-learning model or any other machine-learning model mentioned throughout this disclosure. The report machine learning model may include a Language processing moduleor a LLM as described herein above in. The machine-learning model may be performed using, without limitation, linear machine-learning models such as without limitation logistic regression and/or naive Bayes machine-learning models, nearest neighbor machine-learning models such as k-nearest neighbors machine-learning models, support vector machines, least squares support vector machines, fisher's linear discriminant, quadratic machine-learning models, decision trees, boosted trees, random forest machine-learning model, and the like.

6 FIG. 660 660 660 With continued reference to, in some embodiments, generating the activity report may include generating the activity report using a language processing module. Language processing modulemay include any hardware and/or software module. Language processing modulemay be configured to extract, from the one or more documents, one or more words. One or more words may include, without limitation, strings of one or more characters, including without limitation any sequence or sequences of letters, numbers, punctuation, diacritic marks, engineering symbols, geometric dimensioning and tolerancing (GD&T) symbols, chemical symbols and formulas, spaces, whitespace, and other symbols, including any symbols usable as textual data as described above. Textual data may be parsed into tokens, which may include a simple word (sequence of letters separated by whitespace) or more generally a sequence of characters as described previously. Tokens may be broken up by word, pair of words, sentence, or other delimitation. These tokens may in turn be parsed in various ways. Textual data may be parsed into words or sequences of words, which may be considered words as well. Textual data may be parsed into “n-grams”, where all sequences of n consecutive characters are considered. Any or all possible sequences of tokens or words may be stored as “chains”, for example for use as a Markov chain or Hidden Markov Model.

6 FIG. 660 With continued reference to, language processing modulemay operate to produce a language processing model. Language processing model may include a program automatically generated by computing device and/or language processing module to produce associations between one or more words extracted from at least a document and detect associations, including without limitation mathematical associations, between such words. Associations between language elements, where language elements include for purposes herein extracted words, relationships of such categories to other such term may include, without limitation, mathematical associations, including without limitation statistical correlations between any language element and any other language element and/or language elements. Statistical correlations and/or mathematical associations may include probabilistic formulas or relationships indicating, for instance, a likelihood that a given extracted word indicates a given category of semantic meaning. As a further example, statistical correlations and/or mathematical associations may include probabilistic formulas or relationships indicating a positive and/or negative association between at least an extracted word and/or a given semantic meaning; positive or negative indication may include an indication that a given document is or is not indicating a category semantic meaning. Whether a phrase, sentence, word, or other textual element in a document or corpus of documents constitutes a positive or negative indicator may be determined, in an embodiment, by mathematical associations between detected words, comparisons to phrases and/or words indicating positive and/or negative indicators that are stored in memory at computing device, or the like.

6 FIG. 660 660 With continued reference to, language processing moduleand/or diagnostic engine may generate the language processing model by any suitable method, including without limitation a natural language processing classification algorithm; language processing model may include a natural language process classification model that enumerates and/or derives statistical relationships between input terms and output terms. Algorithm to generate language processing model may include a stochastic gradient descent algorithm, which may include a method that iteratively optimizes an objective function, such as an objective function representing a statistical estimation of relationships between terms, including relationships between input terms and output terms, in the form of a sum of relationships to be estimated. In an alternative or additional approach, sequential tokens may be modeled as chains, serving as the observations in a Hidden Markov Model (HMM). HMMs has used herein are statistical models with inference algorithms that may be applied to the models. In such models, a hidden state to be estimated may include an association between an extracted word, phrases, and/or other semantic units. There may be a finite number of categories to which an extracted word may pertain; an HMM inference algorithm, such as the forward-backward algorithm or the Viterbi algorithm, may be used to estimate the most likely discrete state given a word or sequence of words. Language processing modulemay combine two or more approaches. For instance, and without limitation, machine-learning program may use a combination of Naive-Bayes (NB), Stochastic Gradient Descent (SGD), and parameter grid-searching classification techniques; the result may include a classification algorithm that returns ranked associations.

6 FIG. With continued reference to, generating language processing model may include generating a vector space, which may be a collection of vectors, defined as a set of mathematical objects that can be added together under an operation of addition following properties of associativity, commutativity, existence of an identity element, and existence of an inverse element for each vector, and can be multiplied by scalar values under an operation of scalar multiplication compatible with field multiplication, and that has an identity element is distributive with respect to vector addition, and is distributive with respect to field addition. Each vector in an n-dimensional vector space may be represented by an n-tuple of numerical values. Each unique extracted word and/or language element as described above may be represented by a vector of the vector space. In an embodiment, each unique extracted and/or other language element may be represented by a dimension of vector space; as a non-limiting example, each element of a vector may include a number representing an enumeration of co-occurrences of the word and/or language element represented by the vector with another word and/or language element. Vectors may be normalized, scaled according to relative frequencies of appearance and/or file sizes. In an embodiment associating language elements to one another as described above may include computing a degree of vector similarity between a vector representing each language element and a vector representing another language element; vector similarity may be measured according to any norm for proximity and/or similarity of two vectors, including without limitation cosine similarity, which measures the similarity of two vectors by evaluating the cosine of the angle between the vectors, which can be computed using a dot product of the two vectors divided by the lengths of the two vectors. Degree of similarity may include any other geometric measure of distance between vectors.

6 FIG. 660 660 660 604 604 With continued reference to, language processing modulemay use a corpus of documents to generate associations between language elements in a language processing module, and diagnostic engine may then use such associations to analyze words extracted from one or more documents and determine that the one or more documents indicate significance of a category. In an embodiment, language processing moduleand/or processormay perform this analysis using a selected set of significant documents, such as documents identified by one or more experts as representing good information; experts may identify or enter such documents via graphical user interface, or may communicate identities of significant documents according to any other suitable method of electronic communication, or by providing such identity to other persons who may enter such identifications into processor. Documents may be entered into a computing device by being uploaded by an expert or other persons using, without limitation, file transfer protocol (FTP) or other suitable methods for transmission and/or upload of documents; alternatively or additionally, where a document is identified by a citation, a uniform resource identifier (URI), uniform resource locator (URL) or other datum permitting unambiguous identification of the document, diagnostic engine may automatically obtain the document using such an identifier, for instance by submitting a request to a database or compendium of documents such as JSTOR as provided by Ithaka Harbors, Inc. of New York.

6 FIG. 660 644 648 648 648 648 With continued reference to, in some embodiments, language processing modulemay include a grammatical checker. As used in this disclosure, a “grammatical checker” is a component of language processing module that attempts to verify text (i.e., tokens) for grammatical correctness. In a non-limiting example, grammatical checker may include a program that runs simultaneously in the background of the runtime environment of language processing module while generating structured data report. Grammatical checker may automatically correct structured data reportduring, or after structured data reportgeneration. Correcting structured data reportmay include, without limitation, grammar, spelling, tense, word choice, and the like thereof.

6 FIG. 648 648 648 604 648 648 648 604 648 648 604 648 648 648 652 With continued reference to, additionally, or alternatively, generating structured data reportmay include exporting structured data report. As used in this disclosure, “exporting” is converting, outputting, or otherwise exporting structured data reportusing processor. In some embodiments, exporting structured data reportmay include converting structured data reportinto any data structure described in this disclosure. In some embodiments, exporting structured data reportmay include outputting activity report in a format such as, without limitation, an HTML file, pdf file, text document, word document, and the like thereof. In a non-limiting example, processormay convert text within structured data reportinto one or more HTML tags using a representational state transfer (REST) API, wherein the REST API is an API that conforms to constraints of REST architectural style (i.e., client-server architecture). User (i.e., client) may initiate conversion of structured data reportby requesting server through REST API. Requesting server may include client sending a request such as, without limitation, a POST request and the like. Server may post converted one or more HTML tags to a customer relationship management (CRM) platform, wherein the CRM platform is a system that administer a business or other organization interactions with users through data analysis. CRM platform may include a back-office system containing a plurality of automated processes that is executable by processor. CRM platform may send a unique identifier of exported structured data report, a HTML file containing one or more converted HTML tags, and a URL to exported structured data reportthrough an email. Unique identifier and/or URL to exported structured data reportmay include report linkdescribed above in this disclosure.

7 FIG. 6 FIG. 612 612 612 620 612 624 612 704 704 704 704 612 708 708 708 708 612 712 712 712 712 612 716 716 716 612 616 Referring now to, a block diagram of an exemplary embodiment of structured datais illustrated. Structured datamay include any activity data described in this disclosure. In some embodiments, without limitation, structured datamay include box scoredescribed above in this disclosure. In some embodiments, without limitation, structured datamay include confidence scoredescribed above in this disclosure. In some embodiments, without limitation, structured datamay include a description, wherein the descriptionis detailed information related to the structured data. In some cases, descriptionmay include, without limitation, rules, a schedule, historical information, location data, and the like. In a non-limiting example, descriptionmay specify a location and a time of where an activity is taking place. In some embodiments, without limitation, structured datamay include player data, wherein the player datais data related to activity participants (i.e., players). In some cases, player datamay include, without limitation, player name, team name, player age, years of playing, accomplishments, player statistics, and the like thereof. In a non-limiting example, player datamay include a match history of a player and the player's team along with a win rate. In some embodiments, without limitation, structured datamay include an accident data, wherein the accident datais data related to unexpected or unintentional events. In some cases, accident datamay include, without limitation, weather, injuries, unfortunate incidents and the like. In a non-limiting example, accident datamay include a reason for an activity or event cancellation. In some embodiments, without limitation, structured datamay include activity comments, wherein commentsis data related to spectators' opinions or reaction to the activity. In some cases, commentsmay include, without limitation, spectators' view, explainers' words, online reviews, and the like thereof. In a non-limiting example, commentsmay include a collection of online comments on an event. Additionally, or alternatively, structured datamay be stored in and/or retrieved from activity data sourceas described above in reference to.

8 FIG. 800 804 808 812 804 808 808 804 812 812 808 812 Referring to, an exemplary embodiment of fuzzy set comparisonis illustrated. A first fuzzy setmay be represented, without limitation, according to a first membership functionrepresenting a probability that an input falling on a first rangeof values is a member of the first fuzzy set, where the first membership functionhas values on a range of probabilities such as without limitation the interval [0,1], and an area beneath the first membership functionmay represent a set of values within first fuzzy set. Although first rangeof values is illustrated for clarity in this exemplary depiction as a range on a single number line or axis, first rangeof values may be defined on two or more dimensions, representing, for instance, a Cartesian product between a plurality of ranges, curves, axes, spaces, dimensions, or the like. First membership functionmay include any suitable function mapping first rangeto a probability interval, including without limitation a triangular function defined by two linear elements such as line segments or planes that intersect at or below the top of the probability interval. As a non-limiting example, triangular membership function may be defined as:

a trapezoidal membership function may be defined as:

a sigmoidal function may be defined as:

a Gaussian membership function may be defined as:

and a bell membership function may be defined as:

Persons skilled in the art, upon reviewing the entirety of this disclosure, will be aware of various alternative or additional membership functions that may be used consistently with this disclosure.

8 FIG. 804 816 804 820 824 824 812 804 816 804 816 828 808 820 832 804 816 836 812 824 808 820 828 832 840 840 804 816 Still referring to, first fuzzy setmay represent any value or combination of values as described above, including output from one or more machine-learning models, activity data, and a predetermined class, such as without limitation of activity classification and the like. A second fuzzy set, which may represent any value which may be represented by first fuzzy set, may be defined by a second membership functionon a second range; second rangemay be identical and/or overlap with first rangeand/or may be combined with first range via Cartesian product or the like to generate a mapping permitting evaluation overlap of first fuzzy setand second fuzzy set. Where first fuzzy setand second fuzzy sethave a regionthat overlaps, first membership functionand second membership functionmay intersect at a pointrepresenting a probability, as defined on probability interval, of a match between first fuzzy setand second fuzzy set. Alternatively, or additionally, a single value of first and/or second fuzzy set may be located at a locuson first rangeand/or second range, where a probability of membership may be taken by evaluation of first membership functionand/or second membership functionat that range point. A probability atand/ormay be compared to a thresholdto determine whether a positive match is indicated. Thresholdmay, in a non-limiting example, represent a degree of match between first fuzzy setand second fuzzy set, and/or single values therein with each other or with either set, which is sufficient for purposes of the matching process; for instance, threshold may indicate a sufficient degree of overlap between an output from one or more machine-learning models and/or activity data and a predetermined class, such as without limitation activity classification categorization, for combination to occur as described above. Alternatively, or additionally, each threshold may be tuned by a machine-learning and/or statistical process, for instance and without limitation as described in further detail below.

8 FIG. Further referring to, in an embodiment, a degree of match between fuzzy sets may be used to classify activity data with activity classification. For instance, if an activity classification has a fuzzy set matching activity data fuzzy set by having a degree of overlap exceeding a threshold, processor may classify the activity data as belonging to the activity classification categorization. Where multiple fuzzy matches are performed, degrees of match for each respective fuzzy set may be computed and aggregated through, for instance, addition, averaging, or the like, to determine an overall degree of match.

8 FIG. Still referring to, in an embodiment, activity data may be compared to multiple activity classification categorization fuzzy sets. For instance, activity data may be represented by a fuzzy set that is compared to each of the multiple activity classification categorization fuzzy sets; and a degree of overlap exceeding a threshold between the activity data fuzzy set and any of the multiple activity classification categorization fuzzy sets may cause processor to classify the activity data as belonging to activity classification categorization. For instance, in one embodiment there may be two activity classification categorization fuzzy sets, representing respectively a first activity classification categorization and a second activity classification categorization. First activity classification categorization may have a first fuzzy set; Second activity classification categorization may have a second fuzzy set; and activity data may have activity data fuzzy set. Processor, for example, may compare activity data fuzzy set with each of first activity classification categorization fuzzy set and second activity classification categorization fuzzy set, as described above, and classify an activity data to either, both, or neither of first activity classification categorization nor second activity classification categorization. Machine-learning methods as described throughout may, in a non-limiting example, generate coefficients used in fuzzy set equations as described above, such as without limitation x, c, and σ of a Gaussian set as described above, as outputs of machine-learning methods. Likewise, activity data may be used indirectly to determine a fuzzy set, as activity data fuzzy set may be derived from outputs of one or more machine-learning models that take the activity data directly or indirectly as inputs.

8 FIG. 1 4 FIGS.- Still referring to, a computing device may use a logic comparison program, such as, but not limited to, a fuzzy logic model to determine an activity classification response. An activity classification response may include, but is not limited to, flat, exciting, gripping, unforgettable and the like; each such activity classification response may be represented as a value for a linguistic variable representing activity classification response or in other words a fuzzy set as described above that corresponds to a degree of match of activity classification as calculated using any statistical, machine-learning, or other method that may occur to a person skilled in the art upon reviewing the entirety of this disclosure. In other words, a given element of activity data may have a first non-zero value for membership in a first linguistic variable value and a second non-zero value for membership in a second linguistic variable value. In some embodiments, determining an activity classification categorization may include using a linear regression model. A linear regression model may include a machine learning model. A linear regression model may be configured to map data of activity data, such as degree of compatibility to one or more activity classification parameters. A linear regression model may be trained using a machine learning process. A linear regression model may map statistics such as, but not limited to, quality of activity data to activity classification. In some embodiments, determining an activity classification of activity data may include using an activity classification model. An activity classification model may be configured to input collected data and cluster data to a centroid based on, but not limited to, frequency of appearance, linguistic indicators of quality, and the like. Centroids may include scores assigned to them such that quality of compatibility of activity data may each be assigned a score. In some embodiments activity classification model may include a K-means clustering model. In some embodiments, activity classification model may include a particle swarm optimization model. In some embodiments, determining the activity classification of activity data may include using a fuzzy inference engine. A fuzzy inference engine may be configured to map one or more activity data elements using fuzzy logic. In some embodiments, activity data may be arranged by a logic comparison program into activity classification arrangement. An “activity classification arrangement” as used in this disclosure is any grouping of objects and/or data based on skill level and/or output score. This step may be implemented as described above in. Membership function coefficients and/or constants as described above may be tuned according to classification and/or clustering algorithms. For instance, and without limitation, a clustering algorithm may determine a Gaussian or other distribution of questions about a centroid corresponding to a given level, and an iterative or other method may be used to find a membership function, for any membership function type as described above, that minimizes an average error from the statistically determined distribution, such that, for instance, a triangular or Gaussian membership function about a centroid representing a center of the distribution that most closely matches the distribution. Error functions to be minimized, and/or methods of minimization, may be performed without limitation according to any error function and/or error function minimization process and/or method as described in this disclosure.

8 FIG. 1 Further referring to, an inference engine may be implemented according to input and/or output membership functions and/or linguistic variables. For instance, a first linguistic variable may represent a first measurable value pertaining to activity data, such as a degree of match of activity classification of an element, while a second membership function may indicate a degree of in activity classification of a subject thereof, or another measurable value pertaining to activity data. Continuing the example, an output linguistic variable may represent, without limitation, a score value. An inference engine may combine rules, such as: “if the activity is ‘football” and the score difference is ‘high’, the activity classification is ‘huge win”—the degree to which a given input function membership matches a given rule may be determined by a triangular norm or “T-norm” of the rule or output membership function with the input membership function, such as min (a, b), product of a and b, drastic product of a and b, Hamacher product of a and b, or the like, satisfying the rules of commutativity (T(a, b)=T(b, a)), monotonicity: (T(a, b)≤T(c, d) if a≤c and b≤d), (associativity: T(a, T(b, c))=T(T(a, b), c)), and the requirement that the numberacts as an identity element. Combinations of rules (“and” or “or” combination of rule membership determinations) may be performed using any T-conorm, as represented by an inverted T symbol or “1,” such as max (a, b), probabilistic sum of a and b (a+b−a*b), bounded sum, and/or drastic T-conorm; any T-conorm may be used that satisfies the properties of commutativity: ⊥(a, b)=⊥(b, a), monotonicity: ⊥(a, b)≤⊥(c, d) if a≤c and b≤d, associativity: ⊥(a, ⊥(b, c))=⊥(⊥(a, b), c), and identity element of 0. Alternatively, or additionally T-conorm may be approximated by sum, as in a “product-sum” inference engine in which T-norm is product and T-conorm is sum. A final output score or other fuzzy inference output may be determined from an output membership function as described above using any suitable defuzzification process, including without limitation Mean of Max defuzzification, Centroid of Area/Center of Gravity defuzzification, Center Average defuzzification, Bisector of Area defuzzification, or the like. Alternatively, or additionally, output rules may be replaced with functions according to the Takagi-Sugeno-King (TSK) fuzzy model.

9 FIG. 1 5 FIGS.- 1 5 FIGS.- 1 5 FIGS.- 1 5 FIGS.- 1 5 FIGS.- 900 905 900 910 900 915 900 920 900 925 900 Referring now to, a flow diagram of exemplary methodfor generating an article is illustrated. At step, methodincludes receiving, by a computing device, a content category. This may be implemented as disclosed and with reference to. In some embodiments, the content category comprises a type of article received from a user selection. The content data comprises contextual information. At step, methodincludes receiving, by the computing device, a data file comprising content data. This may be implemented as disclosed and with reference to. The data file may include a plurality of headers related to a plurality of data types. At step, methodincludes importing, by the computing device, the content data from the data file. This may be implemented as disclosed and with reference to. Importing the content data from the data file may include classifying a plurality of desired data of the content data to a plurality of desired headers. Classifying the plurality of desired data may include receiving desired content training data correlating the data file to data files with headers matched to desired data; training a matching machine learning model as a function of the desired content training data; and; outputting the classified a plurality of desired headers to desired data of the content data. At step, methodincludes generating, by the computing device, an article as a function of the imported content data and content category. This may be implemented as disclosed and with reference to. Generating the article may include generating an aggregate article. Generating the article may include inputting the article into a neural network to receive an augmented article. At step, methodincludes exporting, by the computing device, the article. This may be implemented as disclosed and with reference to. Exporting the article may include inputting the article into an API.

10 FIG. 1 9 FIGS.- 1000 1000 1005 Referring now to, an exemplary methodof generating a report is illustrated. Methodincludes stepof receiving, using at least a processor, a plurality of structured data comprising at least an event from a structured data source. In some embodiments, receiving the plurality of structured data from the structured data source may include performing optical character recognition on the plurality of structured data to convert the plurality of structured data to machine-encoded text. This may be implemented as disclosed with respect to.

10 FIG. 1000 1010 With continued reference to, methodincludes a stepof determining, using the at least a processor, an activity classification as a function of the plurality of structured data, wherein the activity classification comprises an activity identifier. In some embodiments, determining the activity classification may include iteratively applying a plurality of activity conditions to the activity data, wherein the plurality of activity conditions are applied from most strict to least strict until one of the plurality of activity conditions is satisfied. In some embodiments, determining the activity classification may include determining the activity classification using a rule-based engine.

10 FIG. 1 9 FIGS.- 1000 1015 With continued reference to, methodincludes a stepof generating, using the at least a processor, a structured data report as a function of the activity identifier. This may be implemented as disclosed with respect to.

10 FIG. 1 9 FIGS.- 1000 1020 With continued reference to, methodincludes a stepof generating, using the at least a processor, a final report using a large language model (LLM), wherein the LLM is configured to receive as input the structured data report and a user prompt and output the final report, wherein generating the final report comprises generating a report link, wherein generating the report link comprises identifying a previous report as a function of a report tag, generating the report link as a function of the previous report, and inserting the report link into the final report. In some embodiments, generating the final report may include inserting at least one report link into the final report. In some embodiments, generating the final report may include tagging the report with a report tag. In some embodiments, generating the final report may include identifying a previous report as a function of the report tag. In some embodiments, generating the final report may include generating the report link as a function of the previous report. In some embodiments, generating the final report inserting the report link into the final article. In some embodiments, identifying the previous report as a function of the report tag comprises locating a unique identifier associated with the previous report in a lookup table using the report tag. This may be implemented as disclosed with respect to.

10 FIG. 1 9 FIGS.- 1000 With continued reference to, methodmay include a step of publishing, by the least a processor, the final report. Publishing the final report may include publishing the final report using a content management system (CMS). Publishing the final report may include receiving, from the CMS, a unique identifier associated with the final report. This may be implemented as disclosed with respect to.

It is to be noted that any one or more of the aspects and embodiments described herein may be conveniently implemented using one or more machines (e.g., one or more computing devices that are utilized as a user computing device for an electronic document, one or more server devices, such as a document server, etc.) programmed according to the teachings of the present specification, as will be apparent to those of ordinary skill in the computer art. Appropriate software coding can readily be prepared by skilled programmers based on the teachings of the present disclosure, as will be apparent to those of ordinary skill in the software art. Aspects and implementations discussed above employing software and/or software modules may also include appropriate hardware for assisting in the implementation of the machine executable instructions of the software and/or software module.

Such software may be a computer program product that employs a machine-readable storage medium. A machine-readable storage medium may be any medium that is capable of storing and/or encoding a sequence of instructions for execution by a machine (e.g., a computing device) and that causes the machine to perform any one of the methodologies and/or embodiments described herein. Examples of a machine-readable storage medium include, but are not limited to, a magnetic disk, an optical disc (e.g., CD, CD-R, DVD, DVD-R, etc.), a magneto-optical disk, a read-only memory “ROM” device, a random access memory “RAM” device, a magnetic card, an optical card, a solid-state memory device, an EPROM, an EEPROM, and any combinations thereof. A machine-readable medium, as used herein, is intended to include a single medium as well as a collection of physically separate media, such as, for example, a collection of compact discs or one or more hard disk drives in combination with a computer memory. As used herein, a machine-readable storage medium does not include transitory forms of signal transmission.

Such software may also include information (e.g., data) carried as a data signal on a data carrier, such as a carrier wave. For example, machine-executable information may be included as a data-carrying signal embodied in a data carrier in which the signal encodes a sequence of instruction, or portion thereof, for execution by a machine (e.g., a computing device) and any related information (e.g., data structures and data) that causes the machine to perform any one of the methodologies and/or embodiments described herein.

Examples of a computing device include, but are not limited to, an electronic book reading device, a computer workstation, a terminal computer, a server computer, a handheld device (e.g., a tablet computer, a smartphone, etc.), a web appliance, a network router, a network switch, a network bridge, any machine capable of executing a sequence of instructions that specify an action to be taken by that machine, and any combinations thereof. In one example, a computing device may include and/or be included in a kiosk.

11 FIG. 1100 1100 1104 1108 1112 1112 shows a diagrammatic representation of one embodiment of a computing device in the exemplary form of a computer systemwithin which a set of instructions for causing a control system to perform any one or more of the aspects and/or methodologies of the present disclosure may be executed. It is also contemplated that multiple computing devices may be utilized to implement a specially configured set of instructions for causing one or more of the devices to perform any one or more of the aspects and/or methodologies of the present disclosure. Computer systemincludes a processorand a memorythat communicate with each other, and with other components, via a bus. Busmay include any of several types of bus structures including, but not limited to, a memory bus, a memory controller, a peripheral bus, a local bus, and any combinations thereof, using any of a variety of bus architectures.

1104 1104 1104 Processormay include any suitable processor, such as without limitation a processor incorporating logical circuitry for performing arithmetic and logical operations, such as an arithmetic and logic unit (ALU), which may be regulated with a state machine and directed by operational inputs from memory and/or sensors; processormay be organized according to Von Neumann and/or Harvard architecture as a non-limiting example. Processormay include, incorporate, and/or be incorporated in, without limitation, a microcontroller, microprocessor, digital signal processor (DSP), Field Programmable Gate Array (FPGA), Complex Programmable Logic Device (CPLD), Graphical Processing Unit (GPU), general purpose GPU, Tensor Processing Unit (TPU), analog or mixed signal processor, Trusted Platform Module (TPM), a floating point unit (FPU), and/or system on a chip (SoC)

1108 1116 1100 1108 1108 1120 1108 Memorymay include various components (e.g., machine-readable media) including, but not limited to, a random-access memory component, a read only component, and any combinations thereof. In one example, a basic input/output system(BIOS), including basic routines that help to transfer information between elements within computer system, such as during start-up, may be stored in memory. Memorymay also include (e.g., stored on one or more machine-readable media) instructions (e.g., software)embodying any one or more of the aspects and/or methodologies of the present disclosure. In another example, memorymay further include any number of program modules including, but not limited to, an operating system, one or more application programs, other program modules, program data, and any combinations thereof.

1100 1124 1124 1124 1112 1124 1100 1124 1128 1100 1120 1128 1120 1104 Computer systemmay also include a storage device. Examples of a storage device (e.g., storage device) include, but are not limited to, a hard disk drive, a magnetic disk drive, an optical disc drive in combination with an optical medium, a solid-state memory device, and any combinations thereof. Storage devicemay be connected to busby an appropriate interface (not shown). Example interfaces include, but are not limited to, SCSI, advanced technology attachment (ATA), serial ATA, universal serial bus (USB), IEEE 1394 (FIREWIRE), and any combinations thereof. In one example, storage device(or one or more components thereof) may be removably interfaced with computer system(e.g., via an external port connector (not shown)). Particularly, storage deviceand an associated machine-readable mediummay provide nonvolatile and/or volatile storage of machine-readable instructions, data structures, program modules, and/or other data for computer system. In one example, softwaremay reside, completely or partially, within machine-readable medium. In another example, softwaremay reside, completely or partially, within processor.

1100 1132 1100 1100 1132 1132 1132 1112 1112 1132 1136 1132 Computer systemmay also include an input device. In one example, a user of computer systemmay enter commands and/or other information into computer systemvia input device. Examples of an input deviceinclude, but are not limited to, an alpha-numeric input device (e.g., a keyboard), a pointing device, a joystick, a gamepad, an audio input device (e.g., a microphone, a voice response system, etc.), a cursor control device (e.g., a mouse), a touchpad, an optical scanner, a video capture device (e.g., a still camera, a video camera), a touchscreen, and any combinations thereof. Input devicemay be interfaced to busvia any of a variety of interfaces (not shown) including, but not limited to, a serial interface, a parallel interface, a game port, a USB interface, a FIREWIRE interface, a direct interface to bus, and any combinations thereof. Input devicemay include a touch screen interface that may be a part of or separate from display, discussed further below. Input devicemay be utilized as a user selection device for selecting one or more graphical representations in a graphical interface as described above.

1100 1124 1140 1140 1100 1144 1148 1144 1120 1100 1140 A user may also input commands and/or other information to computer systemvia storage device(e.g., a removable disk drive, a flash drive, etc.) and/or network interface device. A network interface device, such as network interface device, may be utilized for connecting computer systemto one or more of a variety of networks, such as network, and one or more remote devicesconnected thereto. Examples of a network interface device include, but are not limited to, a network interface card (e.g., a mobile network interface card, a LAN card), a modem, and any combination thereof. Examples of a network include, but are not limited to, a wide area network (e.g., the Internet, an enterprise network), a local area network (e.g., a network associated with an office, a building, a campus or other relatively small geographic space), a telephone network, a data network associated with a telephone/voice provider (e.g., a mobile communications provider data and/or voice network), a direct connection between two computing devices, and any combinations thereof. A network, such as network, may employ a wired and/or a wireless mode of communication. In general, any network topology may be used. Information (e.g., data, software, etc.) may be communicated to and/or from computer systemvia network interface device.

1100 1152 1136 1152 1136 1104 1100 1112 1156 Computer systemmay further include a video display adapterfor communicating a displayable image to a display device, such as display. Examples of a display device include, but are not limited to, a liquid crystal display (LCD), a cathode ray tube (CRT), a plasma display, a light emitting diode (LED) display, and any combinations thereof. Display adapterand displaymay be utilized in combination with processorto provide graphical representations of aspects of the present disclosure. In addition to a display device, computer systemmay include one or more other peripheral output devices including, but not limited to, an audio speaker, a printer, and any combinations thereof. Such peripheral output devices may be connected to busvia a peripheral interface. Examples of a peripheral interface include, but are not limited to, a serial port, a USB connection, a FIREWIRE connection, a parallel connection, and any combinations thereof.

The foregoing has been a detailed description of illustrative embodiments of the invention. Various modifications and additions can be made without departing from the spirit and scope of this invention. Features of each of the various embodiments described above may be combined with features of other described embodiments as appropriate in order to provide a multiplicity of feature combinations in associated new embodiments. Furthermore, while the foregoing describes a number of separate embodiments, what has been described herein is merely illustrative of the application of the principles of the present invention. Additionally, although particular methods herein may be illustrated and/or described as being performed in a specific order, the ordering is highly variable within ordinary skill to achieve methods, systems, and software according to the present disclosure. Accordingly, this description is meant to be taken only by way of example, and not to otherwise limit the scope of this invention.

Exemplary embodiments have been disclosed above and illustrated in the accompanying drawings. It will be understood by those skilled in the art that various changes, omissions and additions may be made to that which is specifically disclosed herein without departing from the spirit and scope of the present invention.